Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.7 (ROCm)

Red Hat AI Inference Server 3.3.7 ROCm is now available. Red Hat® AI Inference Server...

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.3.7 (Spyre)

Red Hat AI Inference Server 3.3.7 Spyre is now available. Red Hat® AI Inference Server...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.3.7 (CUDA)

Red Hat AI Inference Server Model Optimization Tools 3.3.7 CUDA is now available. Red Hat® AI Inference Server Model Optimization Tools...

CVE-2026-92971

InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine. Attackers can submit a migrationrequest with an empty remoteblockids list to trigger an AssertionError that...

CVE-2026-92971 InternLM LMDeploy through 0.17.0 Assertion Denial of Service

InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine. Attackers can submit a migrationrequest with an empty remoteblockids list to trigger an AssertionError that...

PT-2026-94458

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description The inetpeer rate limiting system uses a Red-Black tree to store peer entries keyed deterministically by remote IP address. Since lookups use standard lexicographical comparisons via the...

Inference-Engine Fingerprinting Attacks Are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape

Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced by recent sandbox escapes performed by frontier models at OpenAI and Anthropic. Discussions of how to sandbox inference stack components often foc...

SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

User prompts provided to large language models LLMs may contain sensitive or private information that can be misused by remotely deployed models, such as through inadvertent memorization during retraining. One way to protect user prompts is to execute the LLM inside a trusted execution environmen...

PYSEC-2026-3935 vLLM: Cross-User Data Leak Vulnerability

Summary An integer overflow in the actandmulkernel 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...

vLLM: Cross-User Data Leak Vulnerability

SummaryAn integer overflow in the actandmulkernel 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...

evoke-vllm (>=0.1.0, <=0.1.1), lazyllm-verl (0.3.2.dev1) +3 more potentially affected by CVE-2025-62164 +1 more via vllm (>=0.21.0, <=0.25.1)

vllm PYPI version =0.21.0, =0.1.0, =2.8.0, =2.1.2, =0.1.10, =0.2.2 Source cves: CVE-2025-62164, CVE-2026-73557 Source advisory: OSV:PYSEC-2026-3938...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12570 via keras (2.12.0rc0)

keras PYPI version 2.12.0rc0 is affected by a known vulnerability. The following packages have a transitive dependency on keras and may be impacted: - mlopspython-inference =67580760626172675.0.0, =757069802391466481559610331145 Source cves: CVE-2026-12570 Source advisory: OSV:PYSEC-2026-3856...

pytorch-clip-interrogator (>=2023.2.19.0, <=2023.2.19.1), stochasticx (>=0.0.14, <=0.0.19) +2 more potentially affected by CVE-2026-69112 via accelerate (0.14.0)

accelerate PYPI version 0.14.0 is affected by a known vulnerability. The following packages have a transitive dependency on accelerate and may be impacted: - pytorch-clip-interrogator =2023.2.19.0, =0.0.14, =0.1.0, =0.0.7, =0.0.9 Source cves: CVE-2026-69112 Source advisory: OSV:PYSEC-2026-3804...

GHSA-7M6H-X95X-82Q5 vLLM: Cross-User Data Leak Vulnerability

Summary An integer overflow in the actandmulkernel 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...

EUVD-2026-58066

vLLM: Cross-User Data Leak Vulnerability...

vLLM: Cross-User Data Leak Vulnerability

Summary An integer overflow in the actandmulkernel 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...

CVE-2026-47625

NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could abuse missing authorization. A successful exploit of this vulnerability might lead to information disclosure, data tampering, and denial of service...

CVE-2026-16497

NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause excessive iteration. A successful exploit of this vulnerability might lead to denial of service...

CVE-2026-47625

NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could abuse missing authorization. A successful exploit of this vulnerability might lead to information disclosure, data tampering, and denial of service...

EUVD-2026-72938

NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could abuse missing authorization. A successful exploit of this vulnerability might lead to information disclosure, data tampering, and denial of service...