aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI & LLM Vulnerabilities

Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.

to
Export CSV
110 items

CVE-2026-47625: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could abuse missing authorization. A

highvulnerability
security
Sep 8, 2026
CVE-2026-47625

NVIDIA Triton Inference Server for Linux has a security flaw where missing authorization checks allow attackers to access or modify data and disrupt service. An attacker could exploit this to steal information, change data, or make the system unavailable.

NVD/CVE Database

CVE-2026-16497: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause excessive iteration. A s

highvulnerability
security
Sep 8, 2026
CVE-2026-16497

NVIDIA Triton Inference Server for Linux has a security flaw (CVE-2026-16497) where an attacker can trick the system into repeating operations excessively, potentially causing a denial of service (a situation where a service becomes unavailable to legitimate users).

CVE-2026-49114: In ONNX before 1.21.0, the 'save_external_data' function builds the external-data file path from the model's external_da

highvulnerability
security
Aug 21, 2026
CVE-2026-49114

ONNX (a machine learning model format) versions before 1.21.0 have a vulnerability in the 'save_external_data' function where it unsafely opens files for writing without proper protections. A local attacker with write access to the same directory can create a symlink (a shortcut to another file) that tricks the function into writing to sensitive files like SSH authorization keys or system configuration files instead of the intended target.

CVE-2026-47630: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause an absolute path travers

mediumvulnerability
security
Aug 18, 2026
CVE-2026-47630

NVIDIA Triton Inference Server for Linux contains a vulnerability that allows an attacker to perform absolute path traversal (accessing files outside intended directories by using full file paths), potentially leading to code execution. The vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 4.0. As of the publication date, no detailed information or patch has been provided in this source.

CVE-2026-47629: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause improper input validatio

highvulnerability
security
Aug 18, 2026
CVE-2026-47629

CVE-2026-47629 is a vulnerability in NVIDIA Triton Inference Server for Linux that involves improper input validation (the failure to check that data entering a system is safe and correctly formatted), which could allow an attacker to cause a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a detailed assessment is not yet available.

CVE-2026-47628: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause an allocation of resourc

highvulnerability
security
Aug 18, 2026
CVE-2026-47628

NVIDIA Triton Inference Server for Linux contains a vulnerability (CVE-2026-47628) that allows an attacker to allocate unlimited resources, potentially causing a denial of service (a situation where a system becomes unavailable to legitimate users). The vulnerability is classified as CWE-770, which refers to allocation of resources without limits or throttling (controls that prevent excessive resource use).

CVE-2026-47627: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause path traversal. A succes

criticalvulnerability
security
Aug 18, 2026
CVE-2026-47627

NVIDIA Triton Inference Server for Linux has a path traversal vulnerability (CVE-2026-47627), which is a flaw where an attacker can access files outside of intended directories by manipulating file paths. A successful attack could cause denial of service (making the service unavailable to legitimate users).

CVE-2026-47606: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause an absolute path travers

mediumvulnerability
security
Aug 18, 2026
CVE-2026-47606

CVE-2026-47606 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to perform absolute path traversal (accessing files outside their intended directory by using path tricks like "../"). If successfully exploited, this vulnerability could allow an attacker to run code on the system or access sensitive information.

CVE-2026-27765: Improper input validation for some vLLM Hardware Plugin for Intel(R) Gaudi(R) software before version 0.16.0 within Ring

mediumvulnerability
security
Aug 11, 2026
CVE-2026-27765

A security flaw in vLLM Hardware Plugin for Intel Gaudi software versions before 0.16.0 fails to properly validate user input (check that data is safe before using it), which could allow an authorized user to crash the system through a denial of service attack (making a service unavailable). The flaw affects system availability but not the security of stored data or system integrity.

CVE-2026-20728: Protection mechanism failure for some Intel Extension for TensorFlow software before version 2.15.0.3 within Ring 3: Use

highvulnerability
security
Aug 11, 2026
CVE-2026-20728

A protection mechanism failure in Intel Extension for TensorFlow (a library that adds TensorFlow AI capabilities to Intel systems) before version 2.15.0.3 could allow someone with basic system access to gain higher-level privileges, potentially compromising the confidentiality, integrity, and availability of the system. The attack requires local access and low complexity, with passive user interaction.

CVE-2026-47487: NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repos

mediumvulnerability
security
Aug 4, 2026
CVE-2026-47487

NVIDIA Triton Inference Server for Linux has a vulnerability where an attacker could read, write, or modify files outside the intended model repository by providing a specially crafted path in the model name to the MLflow plugin. This could lead to denial of service (making a system unavailable) and information disclosure (leaking sensitive data).

CVE-2026-47475: NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API where an attacker could trigger a re

mediumvulnerability
security
Jul 14, 2026
CVE-2026-47475

NVIDIA TensorRT-LLM (a tool for running large language models efficiently) contains a vulnerability in its OpenAI-compatible API where an attacker could trigger a reachable assertion (a failed safety check in the code) in the sampler thread, potentially causing the system to crash. This vulnerability could lead to a denial of service attack (making the service unavailable to legitimate users).

CVE-2026-24271: NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause alloc

mediumvulnerability
security
Jul 14, 2026
CVE-2026-24271

NVIDIA TensorRT-LLM (a tool for running large language models efficiently on NVIDIA GPUs) has a vulnerability in its OpenAI-compatible inference API that allows attackers to request unlimited GPU resources without restrictions. This could cause a denial of service (making the system unavailable to legitimate users) by exhausting the GPU's memory and processing power.

CVE-2026-24233: NVIDIA TensorRT-LLM for Linux contains a vulnerability in the restricted unpickler used for model weight deserialization

highvulnerability
security
Jul 14, 2026
CVE-2026-24233

NVIDIA TensorRT-LLM for Linux has a vulnerability in its unpickler (a tool that converts serialized data back into usable objects) that allows local attackers to deserialize untrusted data. A successful attack could lead to code execution, privilege escalation, data tampering, and information disclosure.

CVE-2026-47482: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause missing release of memory

highvulnerability
security
Jul 14, 2026
CVE-2026-47482

CVE-2026-47482 is a memory leak vulnerability (a bug where a program fails to free up memory it's no longer using) in NVIDIA Triton Inference Server for Linux that allows attackers to cause a denial of service (making a service unavailable to legitimate users). The vulnerability stems from the software not properly releasing memory after it's finished using it.

CVE-2026-47481: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause an authentication bypass t

mediumvulnerability
security
Jul 14, 2026
CVE-2026-47481

CVE-2026-47481 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows attackers to bypass authentication (security checks that verify a user's identity) through an alternative path or channel. If successfully exploited, this flaw could let attackers run their own code on the system, gain higher-level access, steal information, or modify data.

CVE-2026-47480: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause an uncaught exception. A s

highvulnerability
security
Jul 14, 2026
CVE-2026-47480

CVE-2026-47480 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to trigger an uncaught exception (an error that the program doesn't handle properly), potentially causing a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a detailed assessment has not yet been provided.

CVE-2026-47479: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause uncontrolled resource cons

highvulnerability
security
Jul 14, 2026
CVE-2026-47479

CVE-2026-47479 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to cause uncontrolled resource consumption (using up all available computing power or memory), potentially leading to a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though a complete assessment from NIST has not yet been provided.

CVE-2026-47478: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause the use of an expired file

highvulnerability
security
Jul 14, 2026
CVE-2026-47478

CVE-2026-47478 is a vulnerability in NVIDIA Triton Inference Server for Linux where an attacker can exploit the use of an expired file descriptor (a reference to an open file that is no longer valid), potentially causing a denial of service (making the service unavailable to legitimate users). The vulnerability has a CVSS 4.0 severity rating, though the exact scoring details have not yet been provided.

CVE-2026-47477: NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause a stack-based buffer overf

highvulnerability
security
Jul 14, 2026
CVE-2026-47477

CVE-2026-47477 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows an attacker to cause a stack-based buffer overflow (a situation where data written to memory exceeds its allocated space, potentially crashing the system). A successful attack could result in denial of service (making the service unavailable to legitimate users).

1 / 6Next
NVD/CVE Database

Fix: Fixed in version 1.21.0. Users should upgrade ONNX to version 1.21.0 or later.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database

Fix: Update to vLLM Hardware Plugin for Intel Gaudi software version 0.16.0 or later.

NVD/CVE Database

Fix: Update Intel Extension for TensorFlow to version 2.15.0.3 or later.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database
NVD/CVE Database