Policy & Safety
Security & Defense – Page 6
AI cybersecurity, vulnerabilities, attacks and military uses of AI.
FilterCompanies & models
Incident list
Attacks, vulnerabilities and defense stories
| Date | Incident | Affected |
|---|---|---|
| Oct 23, 2026 | Shadow AI Risks: Securing Developer Endpoints in LLM Workflows | — |
| Oct 15, 2026 | OpenAI Engineer Arrested for Planting Hidden Recorder | OpenAI |
| Oct 13, 2026 | Anthropic Warns: Self-Replicating AI on IoT Devices by 2026 | Anthropic |
| Oct 13, 2026 | Anthropic: Small AI Models Near Self-Replication on IoT Devices | Anthropic |
| Oct 12, 2026 | UK £90M Cyber Resilience Initiative Counters LLM Threats | — |
| Oct 9, 2026 | Anthropic OSS Scanner: Free AI Security Audits for Open Source | Anthropic, Claude |
Editor's picks
More stories
-
AI Dark Code Leak: Securing the Supply Chain
Explore the risks of AI leaks like a potential Anthropic breach, uncovering ‘dark code’ threats in LLMs. Learn why MLSecOps and AI SBOMs are essential for…
-
Anthropic Denies AI Sabotage in Military Use – Key Insights
Explore Anthropic’s firm denial of sabotage claims against their Claude models in defense applications. This case highlights critical issues in AI supply chain security, urging verifiable…
-
LLMs in Military Decision-Making: Hidden Risks
Explore the shift of Large Language Models (LLMs) from battlefield automation to cognitive advisors in military strategy. Uncover risks like automation bias, escalation, and policy gaps.…
-
OpenAI Acquires Promptfoo for LLM Security
OpenAI’s acquisition of Promptfoo brings open-source LLM evaluation tools in-house, enabling automated security testing and red-teaming. Discover how this strategic move addresses enterprise risks and boosts…
-
OpenAI Acquires Promptfoo: Boosting AI Security
OpenAI’s acquisition of Promptfoo revolutionizes LLM security by integrating automated evaluation into CI/CD pipelines. Learn how this strategic move enhances AI governance, supports DevSecOps teams, and…
-
Gemini AI Misuse: Cyber Threats from Google’s Report
Google’s threat intelligence reveals state actors and cybercriminals experimenting with Gemini AI for phishing and reconnaissance. Discover the implications for security teams and how to build…
-
Anthropic Pentagon Deal: AI Safety Meets National Security
Anthropic is in talks with the U.S. Department of Defense to deploy its Claude AI models for national security. Explore the implications for AI ethics, cloud…
-
OpenAI Drops Military Ban: Defense AI Pivot
OpenAI has quietly removed its ban on military applications from its usage policy, enabling collaborations with the U.S. DoD on cybersecurity and more. Explore the implications…
-
AI Model Extraction: Advanced Defenses Unveiled
Explore the escalating battle against model extraction in AI, where providers deploy multi-layered defenses like anomaly detection and watermarking to protect proprietary models. Understand the stakes…
-
OpenAI Pentagon Deal: AI for National Security Explained
Discover OpenAI’s new partnership with the U.S. Pentagon, focusing on non-weaponized AI for cybersecurity and defense. Explore the policy shift, ethical implications, and impacts on the…
-
OpenAI DoD Agreement: AI Enters Military Landscape
OpenAI’s landmark agreement with the U.S. Department of Defense marks a shift in AI policy, sidelining Anthropic in federal use. Explore the impacts on vendors, ethics,…
-
Anthropic Exposes Distillation Attacks: AI Security Risks
Anthropic uncovers distillation attacks where competitors use its API to steal model capabilities. Learn about the threats to AI IP, detection methods, and defenses shaping the…