1489 matches found
Researchers Find Serious AI Bugs Exposing Meta, Nvidia, and Microsoft Inference Frameworks
Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence AI inference engines, including those from Meta, Nvidia, Microsoft, and open-source PyTorch projects such as vLLM and SGLang. "These vulnerabilities all traced back to t...
CVE-2025-33202
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where an attacker could cause a stack overflow by sending extra-large payloads. A successful exploit of this vulnerability might lead to denial of service...
How Worrying Are Privacy Attacks against Machine Learning?
In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning ML. The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal data used in training comparable to directly releasing tho...
CVE-2025-63353
A vulnerability in FiberHome GPON ONU HG6145F1 RP4423 allows the device's factory default Wi-Fi password WPA/WPA2 pre-shared key to be predicted from the SSID. The device generates default passwords using a deterministic algorithm that derives the router passphrase from the SSID, enabling an...
EUVD-2025-93535
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where an attacker could cause a stack overflow by sending extra-large payloads. A successful exploit of this vulnerability might lead to denial of service...
CVE-2025-33202
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where an attacker could cause a stack overflow by sending extra-large payloads. A successful exploit of this vulnerability might lead to denial of service...
CVE-2025-33202
NVIDIA Triton Inference Server for Linux and Windows contains a vulnerability where an attacker could cause a stack overflow by sending extra-large payloads. A successful exploit of this vulnerability might lead to denial of service...
kernel: information leak via transient execution vulnerability in some AMD processors
A transient execution vulnerability in some AMD processors may allow an attacker to infer data from previous stores, potentially resulting in the leakage of privileged information...
NVIDIA Triton Inference Server 安全漏洞
NVIDIA Triton Inference Server is an open source software from NVIDIA that helps standardize model deployment and deliver fast and scalable AI in production. A security vulnerability exists in NVIDIA Triton Inference Server that stems from an attacker sending an oversized payload could lead to a...
Security Bulletin: NVIDIA Triton Inference Server- November 2025
NVIDIA has released a software update for NVIDIA Triton Inference Server. To protect your system, download and install the latest release from the Triton Inference Server Releases page on GitHub and view the Secure Deployment Considerations Guide. Go to NVIDIA Product Security. Details The...
PT-2025-46377
Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server for Linux and Windows affected versions not specified Description The NVIDIA Triton Inference Server is susceptible to a stack overflow condition triggered by the reception of excessively large payloads...
Microsoft Uncovers 'Whisper Leak' Attack That Identifies AI Chat Topics in Encrypted Traffic
Microsoft has disclosed details of a novel side-channel attack targeting remote language models that could enable a passive adversary with capabilities to observe network traffic to glean details about model conversation topics despite encryption protections under certain circumstances. This...
CVE-2025-64492
SuiteCRM is an open-source, enterprise-ready Customer Relationship Management CRM software application. Versions 8.9.0 and below contain a time-based blind SQL Injection vulnerability. This vulnerability allows an authenticated attacker to infer data from the database by measuring response times,...
USN-7848-1: AMD Microcode vulnerabilities
Oleksii Oleksenko, Cedric Fournet, Jana Hofmann, Boris Köpf, Stavros Volos, and Flavien Solt discovered that some AMD processors may allow an attacker to infer data from previous stores. A local attacker could possibly use this issue to expose sensitive information. This update provides the updat...
USN-7848-1 amd64-microcode vulnerabilities
Oleksii Oleksenko, Cedric Fournet, Jana Hofmann, Boris Köpf, Stavros Volos, and Flavien Solt discovered that some AMD processors may allow an attacker to infer data from previous stores. A local attacker could possibly use this issue to expose sensitive information. This update provides the updat...
Enabling AI Everywhere with Akamai Inference Cloud
...
CVE-2025-62524 PILOS Exposes PHP version
PILOS Platform for Interactive Live-Online Seminars is a frontend for BigBlueButton. PILOS before 4.8.0 exposes the PHP version via the X-Powered-By header, enabling attackers to fingerprint the server and assess potential exploits. This information disclosure vulnerability originates from PHP’s...
Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
Multimodal large language models MLLMs comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation o...
PT-2025-43445
Name of the Vulnerable Software and Affected Versions The product name cannot be determined. affected versions not specified Description The router’s inconsistent response to invalid course IDs allowed attackers to infer which course IDs exist, potentially aiding reconnaissance. This could assist...
CVE-2025-62509
FileRise is a self-hosted web-based file manager with multi-file upload, editing, and batch operations. Prior to version 1.4.0, a business logic flaw in FileRise’s file/folder handling allows low-privilege users to perform unauthorized operations view/delete/modify on files created by other users...