Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍 PyPI

GHSA-4qjh-9fv9-r85r

LOW

Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching

Also known asCVE-2025-46570PYSEC-2025-53
Published
May 28, 2025
Updated
Feb 4, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed

EPSS Exploitation Probability

via FIRST.org ↗
0.2%probability of exploitation in next 30 days
Lower Risk16th percentile+0.07%
0.00%0.25%0.50%0.75%0.0%0.2%Dec 25Apr 26Jun 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

Blast Radius

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

This issue arises from the prefix caching mechanism, which may expose the system to a timing side-channel attack.

Description

When a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). Our tests revealed that the timing differences caused by matching chunks are significant enough to be recognized and exploited.

For instance, if the victim has submitted a sensitive prompt or if a valuable system prompt has been cached, an attacker sharing the same backend could attempt to guess the victim's input. By measuring the TTFT based on prefix matches, the attacker could verify if their guess is correct, leading to potential leakage of private information.

Unlike token-by-token sharing mechanisms, vLLM’s chunk-based approach (PageAttention) processes tokens in larger units (chunks). In our tests, with chunk_size=2, the timing differences became noticeable enough to allow attackers to infer whether portions of their input match the victim's prompt at the chunk level.

Environment

  • GPU: NVIDIA A100 (40G)
  • CUDA: 11.8
  • PyTorch: 2.3.1
  • OS: Ubuntu 18.04
  • vLLM: v0.5.1 Configuration: We launched vLLM using the default settings and adjusted chunk_size=2 to evaluate the TTFT.

Leakage

We conducted our tests using LLaMA2-70B-GPTQ on a single device. We analyzed the timing differences when prompts shared prefixes of 2 chunks, and plotted the corresponding ROC curves. Our results suggest that timing differences can be reliably used to distinguish prefix matches, demonstrating a potential side-channel vulnerability. <img src="https://github.com/user-attachments/assets/db3491e9-02b7-424c-9b6d-56f553b39f2f" alt="roc_curves_combined_block_2" width="400"/>

Results

In our experiment, we analyzed the response time differences between cache hits and misses in vLLM's PageAttention mechanism. Using ROC curve analysis to assess the distinguishability of these timing differences, we observed the following results:

  • With a 1-token prefix, the ROC curve yielded an AUC value of 0.571, indicating that even with a short prefix, an attacker can reasonably distinguish between cache hits and misses based on response times.
  • When the prefix length increases to 8 tokens, the AUC value rises significantly to 0.99, showing that the attacker can almost perfectly identify cache hits with a longer prefix.

Fixes

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllmall versions0.9.0

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update vllm to 0.9.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-4qjh-9fv9-r85r is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether GHSA-4qjh-9fv9-r85r is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to GHSA-4qjh-9fv9-r85r. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

This issue arises from the prefix caching mechanism, which may expose the system to a timing side-channel attack. ## Description When a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). Our tests revealed that the timing differences caused by matching chunks are significant enough to be recognized and exploited. For instance, if the victim has submitted a sensitive prompt or if a valuable system prompt has been cached, an attacker sharing the same backend could attempt to
O3 Security · Impact-Aware SCA

Is GHSA-4qjh-9fv9-r85r in your dependencies?

O3 detects GHSA-4qjh-9fv9-r85r across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.