1314 matches found
CVE-2026-24146
NVIDIA Triton Inference Server contains a vulnerability where insufficient input validation and a large number of outputs could cause a server crash. A successful exploit of this vulnerability might lead to denial of service...
CVE-2024-0391
The check user account lock states feature within the email OTP flow fails to validate user input, allowing an attacker to infer the existence of registered user accounts. The discovery of valid usernames can increase the risk of brute-force and social engineering attacks. Attackers can leverage...
Optimize AI Inference: Real-Time NodeBalancers Metrics for AI Workloads
...
EUVD-2026-33833
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
CVE-2026-10300
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
CVE-2026-10300 SGLang Inference HTTP Endpoint lora_manager.py assertion
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
CVE-2026-10300 SGLang Inference HTTP Endpoint lora_manager.py assertion
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
CVE-2026-10300
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
CVE-2026-10300
SGLang 0.5.10.post1 contains a vulnerability in the Inference HTTP Endpoint, specifically in python/sglang/srt/lora/lora_manager.py where manipulation of the lora_path argument can trigger a reachable assertion. The issue is exposed over the network with high attack complexity and no authenticati...
CVE-2026-49121
CVE-2026-49121 affects AI Tensor Engine for ROCm (AITER) up to version 0.1.14. The vulnerability exists in the MessageQueue.recv() function in shm_broadcast.py, where an unauthenticated remote attacker can deliver a crafted pickle payload to a ZMQ SUB socket (no authentication, no HMAC, no format...
EUVD-2026-33717
AI Tensor Engine for ROCm AITER through 0.1.14 contains an unauthenticated remote code execution vulnerability in the MessageQueue.recv function within shmbroadcast.py that allows unauthenticated remote attackers to execute arbitrary code by sending a malicious pickle payload to a ZMQ SUB socket...
CVE-2026-49121 AI Tensor Engine for ROCm (AITER) 0.1.14 Unauthenticated RCE via MessageQueue.recv() Pickle Deserialization
AI Tensor Engine for ROCm AITER through 0.1.14 contains an unauthenticated remote code execution vulnerability in the MessageQueue.recv function within shmbroadcast.py that allows unauthenticated remote attackers to execute arbitrary code by sending a malicious pickle payload to a ZMQ SUB socket...
sglang 安全漏洞
SGLang is a programming language and runtime system developed by SGL-project, aimed at accelerating large model inference. Version SGLang 0.5.10.post1 contains a security vulnerability. This vulnerability stems from an unknown function in the Inference HTTP Endpoint component file...
SkillGuard: A Permission Framework for Agent Skills
Agent skills extend LLM agents with reusable instructions, scripts, tool bindings, and contextual dependencies. However, current skill ecosystems largely rely on trust-based loading and static inspection, leaving a gap between what a skill can inject into an agent's context and what it can cause...
PT-2026-45663
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/lora manager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lora path leads to reachable assertion. The attack can be launched...
Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms
The need for secure and private Artificial Intelligence AI and Machine Learning ML on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an ever-increasing number of pre-trained AI models being used o...
swimtrack-poc
SwimTrack PoC This directory contains a proof of concept for...
Distributed AI Inference: Why Placement Is the New Bottleneck
In real AI systems, bottlenecks don't disappear, they move. Learn about why inference placement, not raw compute, is the decisive infrastructure question...
On Reliability of Efficient Membership Inference Vulnerability Evaluation
Membership inference attacks MIAs are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through false positive rate FPR and true positive rate TPR of a...
CVE-2026-5817
CVE-2026-5817 affects the vllm-metal backend used by Docker Model Runner on macOS. The backend loads model tokenizers with trust_remote_code=True, causing transformers.AutoTokenizer.from_pretrained() to import and execute arbitrary Python files from models pulled from an OCI registry. This can en...