VulnHub

NVIDIA research shows how agentic AI fails under attack

Help Net Security

NVIDIA's research highlights the vulnerabilities of agentic AI systems, which operate with minimal human oversight. These systems face new risks due to their interactions with various models, tools, and data sources, necessitating a safety and security framework to address these challenges.

Impact: Agentic AI systems, tools, and workflows

Remediation: Implement the safety and security framework proposed by NVIDIA and Lakera AI to assess and mitigate risks.

3 hours ago

Read Original

ShadowRay 2.0 Exploits Unpatched Ray Flaw to Build Self-Spreading GPU Cryptomining Botnet

The Hacker News

Actively Exploited

Oligo Security has reported that the ShadowRay 2.0 attack exploits a two-year-old vulnerability in the Ray AI framework to create a self-replicating cryptocurrency mining botnet using infected NVIDIA GPU clusters. This ongoing threat highlights the severity of unpatched vulnerabilities and the potential for widespread exploitation in the cybersecurity landscape.

Impact: Ray open-source AI framework, NVIDIA GPUs

Remediation: Update the Ray framework to the latest version and apply security patches as they become available.

Vulnerability Botnet

2 weeks ago

Read Original

Articles tagged "NVIDIA"