<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://vulnerability.circl.lu</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Tue, 29 Sep 2026 04:54:34 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-93840 — vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids</title>
      <link>https://vulnerability.circl.lu/vuln/cve-2026-93840</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; vllm-project vllm&lt;/p&gt;
&lt;p&gt;vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; vllm-project vllm&lt;/p&gt;
&lt;p&gt;vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/cve-2026-93840</guid>
    </item>
  </channel>
</rss>
