blog/algorithms/hash-tables/breaking/mitigations/index.html

85 lines
60 KiB
HTML
Raw Normal View History

<!doctype html>
<html lang="en" dir="ltr" class="docs-wrapper plugin-docs plugin-id-algorithms docs-version-current docs-doc-page docs-doc-id-hash-tables/2023-11-28-breaking/mitigations" data-has-hydrated="false">
<head>
<meta charset="UTF-8">
<meta name="generator" content="Docusaurus v3.0.0">
<title data-rh="true">Possible Mitigations | mf</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://blog.mfocko.xyz/algorithms/hash-tables/breaking/mitigations/"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-algorithms-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-algorithms-current"><meta data-rh="true" property="og:title" content="Possible Mitigations | mf"><meta data-rh="true" name="description" content="Talking about the ways how to prevent the attacks on the hash table.
"><meta data-rh="true" property="og:description" content="Talking about the ways how to prevent the attacks on the hash table.
"><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://blog.mfocko.xyz/algorithms/hash-tables/breaking/mitigations/"><link data-rh="true" rel="alternate" href="https://blog.mfocko.xyz/algorithms/hash-tables/breaking/mitigations/" hreflang="en"><link data-rh="true" rel="alternate" href="https://blog.mfocko.xyz/algorithms/hash-tables/breaking/mitigations/" hreflang="x-default"><link data-rh="true" rel="preconnect" href="https://0VXRFPR4QF-dsn.algolia.net" crossorigin="anonymous"><link rel="search" type="application/opensearchdescription+xml" title="mf" href="/opensearch.xml">
<link rel="alternate" type="application/rss+xml" href="/blog/rss.xml" title="mf RSS Feed">
<link rel="alternate" type="application/atom+xml" href="/blog/atom.xml" title="mf Atom Feed">
<link rel="alternate" type="application/json" href="/blog/feed.json" title="mf JSON Feed">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/katex@0.13.24/dist/katex.min.css" integrity="sha384-odtC+0UGzzFL/6PNoE8rX/SPcQDXBJ+uRepguP4QkPCm2LBxH3FA3y+fKSiJ+AmM" crossorigin="anonymous"><link rel="stylesheet" href="/assets/css/styles.0f577c26.css">
<script src="/assets/js/runtime~main.f17742ff.js" defer="defer"></script>
<script src="/assets/js/main.a809bb25.js" defer="defer"></script>
</head>
<body class="navigation-with-keyboard">
<script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return localStorage.getItem("theme")}catch(t){}}();t(null!==e?e:"light")}(),function(){try{const c=new URLSearchParams(window.location.search).entries();for(var[t,e]of c)if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id="__docusaurus"><div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="navbar navbar--fixed-top"><div class="navbar__inner"><div class="navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><b class="navbar__title text--truncate">mf</b></a><div class="navbar__item dropdown dropdown--hoverable"><a href="#" aria-haspopup="true" aria-expanded="false" role="button" class="navbar__link">Additional FI MU materials</a><ul class="dropdown__menu"><li><a aria-current="page" class="dropdown__link dropdown__link--active" href="/algorithms/">Algorithms</a></li><li><a class="dropdown__link" href="/c/">C</a></li><li><a class="dropdown__link" href="/cpp/">C++</a></li></ul></div><a class="navbar__item navbar__link" href="/contributions/">Contributions</a><a class="navbar__item navbar__link" href="/talks/">Talks</a></div><div class="navbar__items navbar__items--right"><a class="navbar__item navbar__link" href="/blog/">Blog</a><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type="button" disabled="" title="Switch between dark and light mode (currently light mode)" aria-label="Switch between dark and light mode (currently light mode)" aria-live="polite"><svg viewBox="0 0 24 24" width="24" height="24" class="lightToggleIcon_pyhR"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" class="darkToggleIcon_wfgR"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg></button></div><div class="navbarSearchContainer_Bca1"><button type="button" class="DocSearch DocSearch-Button" aria-label="Search"><span class="DocSearch-Button-Container"><svg width="20" height="20" class="DocSearch-Search-Icon" viewBox="0 0 20 20"><path d="M14.386 14.386l4.0877 4.0877-4.0877-4.0877c-2.
only make it better, we cannot guarantee the ideal time complexity…</p>
<p>For the sake of simplicity (and referencing an article by <em>Neal Wu</em> on the same
topic; in references below) I will use the C++ to describe the mitigations.</p>
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="random-seed">Random seed<a href="#random-seed" class="hash-link" aria-label="Direct link to Random seed" title="Direct link to Random seed"></a></h2>
<p>One of the options how to avoid this kind of an attack is to introduce a random
seed to the hash. That way it is not that easy to choose the <em>nasty</em> numbers.</p>
<div class="language-cpp codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-cpp codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token keyword" style="color:#00009f">struct</span><span class="token plain"> </span><span class="token class-name">custom_hash</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> size_t </span><span class="token keyword" style="color:#00009f">operator</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">(</span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> x</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">const</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">return</span><span class="token plain"> x </span><span class="token operator" style="color:#393A34">+</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">7529</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">}</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"></span><span class="token punctuation" style="color:#393A34">}</span><span class="token punctuation" style="color:#393A34">;</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div>
<p>As you may have noticed, this is not very helpful, since it just shifts the
issue by some number. Better option is to use a shift from random number
generator:</p>
<div class="language-cpp codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-cpp codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token keyword" style="color:#00009f">struct</span><span class="token plain"> </span><span class="token class-name">custom_hash</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> size_t </span><span class="token keyword" style="color:#00009f">operator</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">(</span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> x</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">const</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">static</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">const</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> FIXED_RANDOM </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> chrono</span><span class="token double-colon punctuation" style="color:#393A34">::</span><span class="token plain">steady_clock</span><span class="token double-colon punctuation" style="color:#393A34">::</span><span class="token function" style="color:#d73a49">now</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">.</span><span class="token function" style="color:#d73a49">time_since_epoch</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">.</span><span class="token function" style="color:#d73a49">count</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">return</span><span class="token plain"> x </span><span class="token operator" style="color:#393A34">+</span><span class="token plain"> FIXED_RANDOM</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">}</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"></span><span class="token punctuation" style="color:#393A34">}</span><span class="token punctuation" style="color:#393A34">;</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7
<p>In this case the hash is using a high-precision clock to shift the number, which
is much harder to break.</p>
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="better-random-seed">Better random seed<a href="#better-random-seed" class="hash-link" aria-label="Direct link to Better random seed" title="Direct link to Better random seed"></a></h2>
<p>Building on the previous solution, we can do some <em>bit magic</em> instead of the
shifting:</p>
<div class="language-cpp codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-cpp codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token keyword" style="color:#00009f">struct</span><span class="token plain"> </span><span class="token class-name">custom_hash</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> size_t </span><span class="token keyword" style="color:#00009f">operator</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">(</span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> x</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">const</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">static</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">const</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> FIXED_RANDOM </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> chrono</span><span class="token double-colon punctuation" style="color:#393A34">::</span><span class="token plain">steady_clock</span><span class="token double-colon punctuation" style="color:#393A34">::</span><span class="token function" style="color:#d73a49">now</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">.</span><span class="token function" style="color:#d73a49">time_since_epoch</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">.</span><span class="token function" style="color:#d73a49">count</span><span class="token punctuation" style="color:#393A34">(</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">^=</span><span class="token plain"> FIXED_RANDOM</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">return</span><span class="token plain"> x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">&gt;&gt;</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">16</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="tok
<p>This not only shifts the number, it also manipulates the underlying bits of the
hash. In this case we&#x27;re also applying the <code>XOR</code> operation.</p>
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="adjusting-the-hash-function">Adjusting the hash function<a href="#adjusting-the-hash-function" class="hash-link" aria-label="Direct link to Adjusting the hash function" title="Direct link to Adjusting the hash function"></a></h2>
<p>Another option is to switch up the hash function.</p>
<p>For example Rust uses <a href="https://en.wikipedia.org/wiki/SipHash" target="_blank" rel="noopener noreferrer"><em>SipHash</em></a> by
default.</p>
<p>On the other hand, you can usually specify your own hash function, here we will
follow the article by <em>Neal</em> that uses so-called <em><code>splitmix64</code></em>.</p>
<div class="language-cpp codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-cpp codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token keyword" style="color:#00009f">static</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> </span><span class="token function" style="color:#d73a49">splitmix64</span><span class="token punctuation" style="color:#393A34">(</span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> x</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token comment" style="color:#999988;font-style:italic">// http://xorshift.di.unimi.it/splitmix64.c</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">+=</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0x9e3779b97f4a7c15</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">&gt;&gt;</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">30</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token operator" style="color:#393A34">*</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0xbf58476d1ce4e5b9</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">&gt;&gt;</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">27</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token operator" style="color:#393A34">*</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0x94d049bb133111eb</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">return</span><span class="token plain"> x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span
<p>As you can see, this definitely doesn&#x27;t do identity on the integers <!-- -->😄</p>
<p>Another example would be
<a href="https://github.com/openjdk/jdk/blob/dc256fbc6490f8163adb286dbb7380c10e5e1e06/src/java.base/share/classes/java/util/HashMap.java#L320-L339" target="_blank" rel="noopener noreferrer"><code>HashMap::hash()</code></a>
function in Java:</p>
<div class="language-java codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-java codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic">/**</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * Computes key.hashCode() and spreads (XORs) higher bits of hash</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * to lower. Because the table uses power-of-two masking, sets of</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * hashes that vary only in bits above the current mask will</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * always collide. (Among known examples are sets of Float keys</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * holding consecutive whole numbers in small tables.) So we</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * apply a transform that spreads the impact of higher bits</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * downward. There is a tradeoff between speed, utility, and</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * quality of bit-spreading. Because many common sets of hashes</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * are already reasonably distributed (so don&#x27;t benefit from</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * spreading), and because we use trees to handle large sets of</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * collisions in bins, we just XOR some shifted bits in the</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * cheapest possible way to reduce systematic lossage, as well as</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * to incorporate impact of the highest bits that would otherwise</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> * never be used in index calculations because of table bounds.</span><br></span><span class="token-line" style="color:#393A34"><span class="token comment" style="color:#999988;font-style:italic"> */</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"></span><span class="token keyword" style="color:#00009f">static</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">final</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">int</span><span class="token plain"> </span><span class="token function" style="color:#d73a49">hash</span><span class="token punctuation" style="color:#393A34">(</span><span class="token class-name">Object</span><span class="token plain"> key</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{
<p>You can notice that they try to include the upper bits of the hash by using
<code>XOR</code>, this would render our attack in the previous part helpless.</p>
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="combining-both">Combining both<a href="#combining-both" class="hash-link" aria-label="Direct link to Combining both" title="Direct link to Combining both"></a></h2>
<p>Can we make it better? Of course! Use multiple mitigations at the same time. In
our case, we will both inject the random value <strong>and</strong> use the <em><code>splitmix64</code></em>:</p>
<div class="language-cpp codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-cpp codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token keyword" style="color:#00009f">struct</span><span class="token plain"> </span><span class="token class-name">custom_hash</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token keyword" style="color:#00009f">static</span><span class="token plain"> </span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> </span><span class="token function" style="color:#d73a49">splitmix64</span><span class="token punctuation" style="color:#393A34">(</span><span class="token keyword" style="color:#00009f">uint64_t</span><span class="token plain"> x</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">{</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> </span><span class="token comment" style="color:#999988;font-style:italic">// http://xorshift.di.unimi.it/splitmix64.c</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">+=</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0x9e3779b97f4a7c15</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">&gt;&gt;</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">30</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token operator" style="color:#393A34">*</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0xbf58476d1ce4e5b9</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> x </span><span class="token operator" style="color:#393A34">=</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">^</span><span class="token plain"> </span><span class="token punctuation" style="color:#393A34">(</span><span class="token plain">x </span><span class="token operator" style="color:#393A34">&gt;&gt;</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">27</span><span class="token punctuation" style="color:#393A34">)</span><span class="token punctuation" style="color:#393A34">)</span><span class="token plain"> </span><span class="token operator" style="color:#393A34">*</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">0x94d049bb133111eb</span><span class="token punctuation" style="color:#393A34">;</span><span class="token plain"></span><br
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="fallback-for-extreme-cases">Fallback for extreme cases<a href="#fallback-for-extreme-cases" class="hash-link" aria-label="Direct link to Fallback for extreme cases" title="Direct link to Fallback for extreme cases"></a></h2>
<p>As we have mentioned above, Python resolves the conflicts by probing (it looks
for empty space somewhere else in the table, but it&#x27;s deterministic about it, so
it&#x27;s not “<em>oops, this is full, let&#x27;s go one-by-one and find some spot</em>”). In the
case of C++ and Java, they resolve the conflicts by linked lists, as is the
usual text-book depiction of the hash table.</p>
<p>However Java does something more intelligent. Once you go over the threshold of
conflicts in one spot, it converts the linked list to an RB-tree that is sorted
by the hash and key respectively.</p>
<div class="theme-admonition theme-admonition-tip admonition_xJq3 alert alert--success"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 12 16"><path fill-rule="evenodd" d="M6.5 0C3.48 0 1 2.19 1 5c0 .92.55 2.25 1 3 1.34 2.25 1.78 2.78 2 4v1h5v-1c.22-1.22.66-1.75 2-4 .45-.75 1-2.08 1-3 0-2.81-2.48-5-5.5-5zm3.64 7.48c-.25.44-.47.8-.67 1.11-.86 1.41-1.25 2.06-1.45 3.23-.02.05-.02.11-.02.17H5c0-.06 0-.13-.02-.17-.2-1.17-.59-1.83-1.45-3.23-.2-.31-.42-.67-.67-1.11C2.44 6.78 2 5.65 2 5c0-2.2 2.02-4 4.5-4 1.22 0 2.36.42 3.22 1.19C10.55 2.94 11 3.94 11 5c0 .66-.44 1.78-.86 2.48zM4 14h5c-.23 1.14-1.3 2-2.5 2s-2.27-.86-2.5-2z"></path></svg></span>tip</div><div class="admonitionContent_BuS1"><p>You may wonder what sense does it make to define an ordering on the tree by the
hash, if we&#x27;re dealing with conflicts. Well, there are less buckets than the
range of the hash, so if we take lower bits, we can have a conflict even though
the hashes are not the same.</p></div></div>
<p>You might have noticed that if we get a <strong>really bad</strong> hashing function, this is
not very helpful. It is not, <strong>but</strong> it can help in other cases.</p>
<div class="theme-admonition theme-admonition-danger admonition_xJq3 alert alert--danger"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 12 16"><path fill-rule="evenodd" d="M5.05.31c.81 2.17.41 3.38-.52 4.31C3.55 5.67 1.98 6.45.9 7.98c-1.45 2.05-1.7 6.53 3.53 7.7-2.2-1.16-2.67-4.52-.3-6.61-.61 2.03.53 3.33 1.94 2.86 1.39-.47 2.3.53 2.27 1.67-.02.78-.31 1.44-1.13 1.81 3.42-.59 4.78-3.42 4.78-5.56 0-2.84-2.53-3.22-1.25-5.61-1.52.13-2.03 1.13-1.89 2.75.09 1.08-1.02 1.8-1.86 1.33-.67-.41-.66-1.19-.06-1.78C8.18 5.31 8.68 2.45 5.05.32L5.03.3l.02.01z"></path></svg></span>danger</div><div class="admonitionContent_BuS1"><p>As the ordering on the keys of the hash table is not required and may not be
implemented, the tree may be ordered by just the hash.</p></div></div>
<hr>
<h2 class="anchor anchorWithStickyNavbar_LWe7" id="references">References<a href="#references" class="hash-link" aria-label="Direct link to References" title="Direct link to References"></a></h2>
<ol>
<li>Neal Wu.
<a href="https://codeforces.com/blog/entry/62393" target="_blank" rel="noopener noreferrer">Blowing up <code>unordered_map</code>, and how to stop getting hacked on it</a>.</li>
</ol></div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="theme-doc-footer-tags-row row margin-bottom--sm"><div class="col"><b>Tags:</b><ul class="tags_jXut padding--none margin-left--sm"><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/algorithms/tags/cpp/">cpp</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/algorithms/tags/python/">python</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/algorithms/tags/hash-tables/">hash-tables</a></li></ul></div></div><div class="theme-doc-footer-edit-meta-row row"><div class="col"><a href="https://github.com/mfocko/blog/tree/main/algorithms/12-hash-tables/2023-11-28-breaking/02-mitigations.md" target="_blank" rel="noopener noreferrer" class="theme-edit-this-page"><svg fill="currentColor" height="20" width="20" viewBox="0 0 40 40" class="iconEdit_Z9Sw" aria-hidden="true"><g><path d="m34.5 11.7l-3 3.1-6.3-6.3 3.1-3q0.5-0.5 1.2-0.5t1.1 0.5l3.9 3.9q0.5 0.4 0.5 1.1t-0.5 1.2z m-29.5 17.1l18.4-18.5 6.3 6.3-18.4 18.4h-6.3v-6.2z"></path></g></svg>Edit this page</a></div><div class="col lastUpdated_vwxv"><span class="theme-last-updated">Last updated<!-- --> on <b><time datetime="2023-11-28T00:00:00.000Z">Nov 28, 2023</time></b></span></div></div></footer></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/algorithms/hash-tables/breaking/python/"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Breaking Python</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#random-seed" class="table-of-contents__link toc-highlight">Random seed</a></li><li><a href="#better-random-seed" class="table-of-contents__link toc-highlight">Better random seed</a></li><li><a href="#adjusting-the-hash-function" class="table-of-contents__link toc-highlight">Adjusting the hash function</a></li><li><a href="#combining-both" class="table-of-contents__link toc-highlight">Combining both</a></li><li><a href="#fallback-for-extreme-cases" class="table-of-contents__link toc-highlight">Fallback for extreme cases</a></li><li><a href="#references" class="table-of-contents__link toc-highlight">References</a></li></ul></div></div></div></div></main></div></div></div><footer class="footer footer--dark"><div class="container container-fluid"><div class="row footer__links"><div class="col footer__col"><div class="footer__title">Git</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://github.com/mfocko" target="_blank" rel="noopener noreferrer" class="footer__link-item">GitHub<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li class="footer__item"><a href="https://gitlab.com/mfocko" target="_blank" rel="noopener noreferrer" class="footer__link-item">GitLab<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li><li class="footer__item"><a href="https://git.mfocko.xyz/mfocko" target="_blank" rel="noopener noreferrer" class="footer__link-item">Gitea (self-hosted)<svg width="13.5" height="13.5" aria-hidden="true" viewBox="0 0 24 24" class="iconExternalLink_nPIU"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"></path></svg></a></li></ul></div><div class="col footer__col"><div class="footer__title">Social #1</div><ul class="footer__items clean-list"><li class="footer__item"><a href="https://www.linkedin.com/in/mfocko/" target="_blank" rel="noopener noreferrer"
</body>
</html>