Lucene search
K

1255 matches found

Akamai Blog
Akamai Blog
added 2 days ago2 views

Optimize AI Inference: Real-Time NodeBalancers Metrics for AI Workloads

...

5.8AI score
Exploits0
EUVD
EUVD
added 3 days ago7 views

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...

6.3CVSS5.2AI score0.00047EPSS
Exploits0References7
NVD
NVD
added 4 days ago7 views

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...

6.3CVSS0.00047EPSS
Exploits0References6
CVE
CVE
added 4 days ago16 views

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...

6.3CVSS5.2AI score0.00047EPSS
Exploits0References6
Cvelist
Cvelist
added 4 days ago23 views

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...

6.3CVSS0.00047EPSS
Exploits0References6
ATTACKERKB
ATTACKERKB
added 4 days ago6 views

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...

6.3CVSS5.2AI score0.00047EPSS
Exploits0References6
Vulnrichment
Vulnrichment
added 4 days ago5 views

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...

6.3CVSS5.2AI score0.00047EPSS
Exploits0References6
EUVD
EUVD
added 4 days ago9 views

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...

9.2CVSS6.7AI score0.00245EPSS
Exploits0References3
CVE
CVE
added 4 days ago10 views

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...

9.2CVSS6.7AI score0.00245EPSS
Exploits0References3
Cvelist
Cvelist
added 4 days ago24 views

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...

9.2CVSS0.00245EPSS
Exploits0References3
Packet Storm News
Packet Storm News
added 4 days ago1 views

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...

5.8AI score
Exploits0
CNNVD
CNNVD
added 4 days ago4 views

SGLang security vulnerabilities

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...

6.3CVSS5.8AI score0.00047EPSS
Exploits0References6
Positive Technologies
Positive Technologies
added 4 days ago7 views

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...

6.3CVSS5.2AI score0.00047EPSS
Exploits0References7
Packet Storm News
Packet Storm News
added 2026/05/28 12:0 a.m.8 views

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...

5.8AI score
Exploits0
GithubExploit
GithubExploit
added 2026/05/27 8:57 p.m.46 views

swimtrack-poc

SwimTrack PoC This directory contains a proof of concept for...

5.8AI score
Exploits0
Akamai Blog
Akamai Blog
added 2026/05/27 9:0 a.m.5 views

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...

5.8AI score
Exploits0
Packet Storm News
Packet Storm News
added 2026/05/25 12:0 a.m.6 views

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...

5.8AI score
Exploits0
EUVD
EUVD
added 2026/05/22 7:24 p.m.6 views

EUVD-2026-31493

The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trustremotecode=True when loading model tokenizers, and runs without sandboxing. This causes transformers.AutoTokenizer.frompretrained to import and execute arbitrary Python files included in any model pulled fr...

8.8CVSS6.5AI score0.0002EPSS
Exploits1References1
CVE
CVE
added 2026/05/22 7:24 p.m.14 views

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...

8.8CVSS6.5AI score0.0002EPSS
Exploits1References1Affected Software1
Packet Storm News
Packet Storm News
added 2026/05/22 12:0 a.m.6 views

AI Security Research Should Better Incentivize Defense Research

This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...

5.8AI score
Exploits0
Rows per page
Query Builder