PYSEC-2026-3935

Vulnerability from pysec - Published: 2026-09-10 09:45 - Updated: 2026-09-10 11:02
VLAI
Details

Summary

An integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user's inference result, resulting in cross-user data leakage.

Details

The root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82.

As a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A's output to contain portions of User B's inference result. In some cases, User B's response may be copied entirely into User A's response.

This constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.

PoC

We reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.

Using the following configuration:

Batch size: 17 Sequence length: 16384

The final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.

Impact

This vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim's request and cause the victim's inference output to be copied into the attacker's response.

As a result, sensitive information contained in another user's model response may be exposed to an unauthorized party.

Versions

For versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.

Impacted products
Name purl
vllm pkg:pypi/vllm

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.27.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.11.0",
        "0.11.1",
        "0.11.2",
        "0.12.0",
        "0.13.0",
        "0.14.0",
        "0.14.1",
        "0.15.0",
        "0.15.1",
        "0.16.0",
        "0.17.0",
        "0.17.1",
        "0.18.0",
        "0.18.1",
        "0.19.0",
        "0.19.1",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.20.0",
        "0.20.1",
        "0.20.2",
        "0.21.0",
        "0.22.0",
        "0.22.1",
        "0.23.0",
        "0.24.0",
        "0.25.0",
        "0.25.1",
        "0.26.0",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-73558",
    "GHSA-7m6h-x95x-82q5"
  ],
  "details": "### Summary\nAn integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user\u0027s inference result, resulting in cross-user data leakage.\n\n\n### Details\nThe root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82. \n\nAs a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A\u0027s output to contain portions of User B\u0027s inference result. In some cases, User B\u0027s response may be copied entirely into User A\u0027s response.\n\nThis constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.\n### PoC\nWe reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.\n\nUsing the following configuration:\n\nBatch size: 17\nSequence length: 16384\n\nThe final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.\n\n### Impact\nThis vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim\u0027s request and cause the victim\u0027s inference output to be copied into the attacker\u0027s response.\n\nAs a result, sensitive information contained in another user\u0027s model response may be exposed to an unauthorized party.\n\n### Versions\n\nFor versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.",
  "id": "PYSEC-2026-3935",
  "modified": "2026-09-10T11:02:35.628775Z",
  "published": "2026-09-10T09:45:00.769969Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7m6h-x95x-82q5"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-73558"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/issues/42860"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/49660"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/451227cb3ff07989698fed982c2d3e4300257924"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.27.0"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-7m6h-x95x-82q5"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM: Cross-User Data Leak Vulnerability"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Events included in the timeline

Loading timeline…


    Loading…

    Loading…

    Loading…

    Related by attack behaviour

    Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.