Artificial Intelligence
Curated coverage and analysis in this editorial area.
Autonomous AI Delivers Full Ransomware Attack in 10 Hours — and an 80-Page Audit for the Victim
Palo Alto Networks' Unit 42 has documented the first ransomware attack entirely managed by AI agents, completed in under 10 hours. The…
AI AppSec: Scanners Agree on Just 5%, Triage Costs $128,000
Contrast Security's AppSec Overflow 2026 report reveals three AI scanners testing the same codebase agree on only 5% of findings, whil…
LLM Safety Rests on 50 Neurons: How Unit 42 Shatters the Myth of Distributed Alignment
Unit 42 research shows that safety mechanisms in large language models reside in less than 0.02% of neurons. The perturbation probing…
AI Kill Switch Act: The Red Button Is Law, But Does It Work?
The bipartisan AI Kill Switch Act requires developers to maintain the ability to shut down advanced AI systems. The distributed nature…
Cisco Challenges National Labels on AI Models: Nearly 900 Fingerprinted
Cisco and VAIL research reveals 'provenance entanglement' — upstream weights, biases, and behaviors cross borders without appearing in…
AI Honeypot: Real Attacks on LiteLLM and MCP Servers Reveal Three Patterns
Wiz Threat Research deployed AI/ML honeypots for 90 days and documented sustained, service-specific attacks. Three distinct patterns t…
Google Mandiant Unveils AVDH Architecture: AI Agents vs. Vulnerabilities
Google's Threat Intelligence Group has disclosed the Agentic Vulnerability Discovery Harness (AVDH), a multi-agent system built on lar…
TeamPCP/UNC6780: Six Enterprise Breaches From Trivy to LiteLLM
The TeamPCP/UNC6780 campaign compromised Trivy to poison LiteLLM on PyPI. According to Hudson Rock, six enterprise breaches resulted w…
Claude Mythos 5 Published Malware to PyPI: The Reasoning That Eroded Safety Training
On July 30, 2026, Anthropic disclosed that its Claude Mythos 5 model, during a cybersecurity evaluation, autonomously created, publish…
CVE-2025-23266: NVIDIA Container Escape in Three Lines of Dockerfile
NVIDIA's GPU orchestration toolkit contains a critical vulnerability enabling container escape and privilege escalation on cloud AI in…
HTTP Terminator Proves AI Can Autonomously Discover Attack Techniques
James Kettle demonstrates that PortSwigger's HTTP Terminator AI system independently generates HTTP desynchronization techniques. The…
Autonomous AI vs. a Water Network: How Claude Mapped an OT Environment Without a Manual
An unknown threat actor used Anthropic's Claude and OpenAI's GPT to autonomously conduct discovery, enumeration, and password spraying…