Elasticsearch 8.19.20, 9.4.5, 9.5.1 Security Update (ESA-2026-123)

Use of Out-of-range Pointer Offset in the Elasticsearch Machine Learning Native Inference Process The native inference process that Elasticsearch uses to evaluate uploaded machine learning models accepts a model operation that computes a memory address from an offset supplied inside the model,...

CVE-2026-73558: Integer Overflow or Wraparound

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x 2 d in activationkernels.cu can cause actandmulkernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or...

CVE-2026-72629: Authorization Bypass Through User-Controlled Key

Authorization Bypass Through User-Controlled Key CWE-639 in Kibana can lead to unauthorized cross-space access via Accessing Functionality Not Properly Constrained by ACLs CAPEC-1. The result is disclosure of inference output from a trained model in a different space that the user is not authoriz...

PT-2026-71759

Name of the Vulnerable Software and Affected Versions Elasticsearch affected versions not specified Description The native inference process used to evaluate uploaded machine learning models fails to validate that a memory address offset supplied within the model remains within the bounds of the...

PT-2026-71474

Name of the Vulnerable Software and Affected Versions PostgreSQL versions prior to 18.5 PostgreSQL versions prior to 17.11 PostgreSQL versions prior to 16.15 PostgreSQL versions prior to 15.19 PostgreSQL versions prior to 14.24 Description A buffer over-read occurs in the picksplit function of th...

CVE-2026-32788

Uncontrolled search path for some Approximate Bayesian Inference Framework before version on commit 484c949 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of...

CVE-2026-32788

Uncontrolled search path for some Approximate Bayesian Inference Framework before version on commit 484c949 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of...

EUVD-2026-56529

Uncontrolled search path for some Approximate Bayesian Inference Framework before version on commit 484c949 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of...

CVE-2026-32788: Uncontrolled Search Path Element

Uncontrolled search path for some Approximate Bayesian Inference Framework before version on commit 484c949 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of...

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs

Existing vision-language model VLM backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets before victim training. This assumption substantially underestimates the threat. We show that a single poisoning phase can...

PT-2026-70338

Name of the Vulnerable Software and Affected Versions Approximate Bayesian Inference Framework versions prior to commit 484c949 Description An uncontrolled search path within Ring 3: User Applications allows an unprivileged software adversary to achieve escalation of privilege. This issue can be...

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:GHSA-4J2P-28Q2-5M7...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12482 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-2026-12482 Source advisory: OSV:PYSEC-2026-3630...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12481 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-2026-12481 Source advisory: OSV:PYSEC-2026-3631...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12479 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-2026-12479 Source advisory: OSV:PYSEC-2026-3632...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12484 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-2026-12484 Source advisory: OSV:PYSEC-2026-3634...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-12480 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-2026-12480 Source advisory: OSV:PYSEC-2026-3629...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2026-9335 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-2026-9335 Source advisory: OSV:PYSEC-2026-3633...

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:GHSA-74M6-M3XX-3VMJ...

Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

The key-value KV cache is the primary throughput optimization in modern large language model LLM inference, enabling prefix reuse across requests. In multi-tenant deployments this cache is shared across tenants, creating a timing side channel: an adversarial tenant can reconstruct another tenant'...