ai-security

A Google Deepmind paper introduces the first systematic framework for 'AI agent traps'—attacks that exploit autonomous agents' vulnerabilities to external tools and internet access. The researchers identify six attack categories targeting perception, reasoning, memory, actions, multi-agent networks, and human supervisors, with proof-of-concept demonstrations for each.

OpenAI has released Codex Security as a research preview, an AI application security agent designed to detect and patch complex code vulnerabilities. The tool analyzes project context to reduce noise and increase confidence in vulnerability detection.

OpenAI is acquiring Promptfoo, an AI security platform that helps enterprises identify and remediate vulnerabilities in AI systems during development. Terms of the acquisition were not disclosed.

OpenAI is acquiring Promptfoo, an AI security platform, to integrate automated vulnerability testing directly into its Frontier enterprise offering. The acquisition adds jailbreak detection, prompt injection testing, and data leak identification capabilities to OpenAI's enterprise product.

Anthropic's Claude AI has identified over 100 security vulnerabilities in Firefox, including previously undetected bugs that traditional testing methods missed over decades. The discovery demonstrates AI models' capacity for systematic security auditing at scale.

Anthropic has released Claude Code Security, an AI tool designed to identify code vulnerabilities that traditional security scanners overlook. The announcement prompted an immediate decline in cybersecurity stock valuations.