The Nvidia-led coalition aims to give defenders more open tools for testing, auditing and protecting AI models and agents.
The post Nvidia and Tech Giants Launch AI Security Alliance appeared first on SecurityWeek.
Chipmaker Patch Tuesday: Over 60 Vulnerabilities Patched by Intel
Intel, AMD and Nvidia have published security advisories describing vulnerabilities found recently in their products.
The post Chipmaker Patch Tuesday: Over 60 Vulnerabilities Patched by Intel appeared first on SecurityWeek.
Fortinet, Ivanti, Nvidia Release Security Updates
High-severity vulnerabilities could lead to remote code execution, privilege escalation, information disclosure, and configuration tampering.
The post Fortinet, Ivanti, Nvidia Release Security Updates appeared first on SecurityWeek.
Nvidia Triton Vulnerabilities Pose Big Risk to AI Models
Nvidia has patched over a dozen vulnerabilities in Triton Inference Server, including another set of vulnerabilities that threaten AI systems.
The post Nvidia Triton Vulnerabilities Pose Big Risk to AI Models appeared first on SecurityWeek.
Critical Nvidia Toolkit Flaw Exposes AI Cloud Services to Hacking
Wiz researchers discovered NVIDIAScape, an Nvidia Container Toolkit flaw that can be exploited for full control of the host machine.
The post Critical Nvidia Toolkit Flaw Exposes AI Cloud Services to Hacking appeared first on SecurityWeek.
Rowhammer Attack Demonstrated Against Nvidia GPU
Researchers demonstrated GPUHammer — a Rowhammer attack against GPUs — by degrading the accuracy of machine learning models.
The post Rowhammer Attack Demonstrated Against Nvidia GPU appeared first on SecurityWeek.
Trend Micro Flags Incomplete Nvidia Patch That Leaves AI Containers Exposed
Trend Micro researchers flagging problems with Nvidia’s patch for a critical, code execution vulnerability in the Nvidia Container Toolkit.
The post Trend Micro Flags Incomplete Nvidia Patch That Leaves AI Containers Exposed appeared first on SecurityWeek.
Nvidia Riva Vulnerabilities Allow Unauthorized Use of AI Services
Vulnerabilities in Nvidia Riva could allow hackers to abuse speech and translation AI services that are typically expensive.
The post Nvidia Riva Vulnerabilities Allow Unauthorized Use of AI Services appeared first on SecurityWeek.
Critical Nvidia Container Flaw Exposes Cloud AI Systems to Host Takeover
Nvidia confirms risk of code execution, denial of service, escalation of privileges, information disclosure, and data tampering. CVSS 9/10.
The post Critical Nvidia Container Flaw Exposes Cloud AI Systems to Host Takeover appeared first on SecurityWeek.
Nvidia Patches High-Severity Vulnerabilities in AI, Networking Products
Nvidia has patched high-severity vulnerabilities in its Jetson, Mellanox OS, OnyX, Skyway, and MetroX products.
The post Nvidia Patches High-Severity Vulnerabilities in AI, Networking Products appeared first on SecurityWeek.
