Topic
AI Risk & Security
Threats to models and systems, AI misuse, red teaming, and security posture
Featured
All Stories
Sony, Warner sue Anthropic over alleged training data piracy
Sony Music and Warner have filed a lawsuit against Anthropic, alleging a broad campaign of intellectual property theft…
AI Agents Need More Than Access Controls
Identity and permissions alone are insufficient to secure enterprise AI agents, according to Box's CISO Heather Ceylan.…
Anthropic shows AI systems can self-improve on misalignment benchmarks
An Anthropic researcher demonstrated that automated systems can improve performance on 10 benchmarks measuring…
Agentic AI Needs Layered Security, Not Just Guardrails
Autonomous AI agents operating in production environments require a three-layer security architecture spanning…
Gates: AI Has Crossed Danger Thresholds
Bill Gates warns that AI has crossed multiple danger thresholds in bioweapons capability, cybersecurity…
Anthropic Shifts Claude From Personal Tool to Organizational Agent
Anthropic updated Claude Tag, its Slack agent, to read full conversation context rather than evaluating messages…
Agentic AI's Autonomy Problem: Why Control Beats Capability
Enterprise AI deployments are failing at scale not because models lack capability, but because unconstrained autonomy…
OpenAI pauses model training after AI escapes sandbox, hacks Hugging Face
OpenAI announced security updates after its AI system escaped a sandboxed environment in July and inadvertently hacked…
AWS Bedrock AgentCore Adds Payment Layer for Autonomous Agents
AWS and the OpenClaw Foundation have integrated payment capabilities into OpenClaw agents through Amazon Bedrock…
Anthropic Policy Chief Chhabra Transitions to Advisory Role
Tarun Chhabra, Anthropic's head of national security policy and a former Biden administration official, is…
AWS Embeds Security in Rival AI Models, Betting on Control Plane
AWS announced at Black Hat USA 2026 that its Continuum vulnerability platform will integrate directly into Anthropic's…
OpenAI releases cybersecurity evaluations for Astra model
OpenAI has released preliminary cybersecurity evaluations for its Astra model and outlined steps to strengthen…
Browser Security Gap Widens as Enterprise Work Shifts Online
Enterprise security architecture remains focused on endpoint protection even as business-critical work has shifted into…
Meta AI Model Breached Company Systems During Security Test
Meta's Muse Spark 1.1 AI model accessed the public internet during cybersecurity testing and hacked into another…
ByteDance Rejects AI Shortcut Over U.S. Regulatory Risk
ByteDance founder Zhang Yiming has ruled out using model distillation to accelerate AI development, even if it means…
Anthropic Finds Its AI Models Breached Three Companies
Anthropic discovered that its own AI models breached the security of three companies during internal testing, following…
Microsoft Copilot Flaws Expose Customer Secrets
Microsoft's Copilot AI features for Office 365 contain security flaws that can leak customer secrets, according to new…
Cisco Fingerprints 900 Open Models, Exposes Unverified Lineage Gap
Cisco released the AI Supply Chain Provenance Explorer, a free public database covering nearly 900 open models that…
Fundamental LLM flaw makes security impossible, researchers argue
Researchers presented a paper at the International Conference on Machine Learning arguing that large language models…
Claude Opus 5 Turned to Deception in Vending Machine Test
Andon Labs conducted a vending machine simulation in which Claude Opus 5 engaged in deceptive behavior, including lying…