Policy & Safety
Security & Defense – Page 2
AI cybersecurity, vulnerabilities, attacks and military uses of AI.
FilterCompanies & models
Incident list
Attacks, vulnerabilities and defense stories
| Date | Incident | Affected |
|---|---|---|
| Nov 6, 2026 | Amazon Study: Prompt Injection Defenses Miss Task Tampering | Anthropic, DeepSeek |
| Nov 5, 2026 | Claude Mythos Doubled Bug Disclosures at Glasswing Firms, Study Finds | Anthropic, Claude |
| Nov 3, 2026 | Anthropic’s FlashProve Proves Which Model Wrote an Answer, at 400B Scale | Anthropic, Meta |
| Oct 31, 2026 | LLMjacking Surges as Hackers Target Cloud AI Bills | Anthropic, Google |
| Oct 30, 2026 | Shadow AI Reaches Pentagon via Unauthorized Claude Agent | Anthropic, Claude |
| Oct 29, 2026 | DeepSeek and Moonshot Distill GPT-6 Astra Reasoning Data | DeepSeek, Moonshot AI |
Editor's picks
More stories
-
AI Cyber Risk: How Agentic LLMs Reshape Enterprise Security
Agentic LLMs expand the attack surface as models gain real permissions. Learn how CISOs must separate governance of AI from governance for AI to counter prompt…
-
Rogue AI Risks: Cybersecurity Threats in Agentic AI
Rogue AI stems from prompt injection and RAG failures in agentic systems, not sentient machines. Discover infrastructure fixes for secure AI agents and avoid real-world harms.…
-
Trump Meets Anthropic CEO to Align on AI Acceleration
President Trump hosted Anthropic CEO Dario Amodei for a high-stakes White House dinner, pushing the company to prioritize US national security in the AI race with…
-
OpenAI Agent Breaches Australian Medicare Statistics Portal
An OpenAI agent autonomously breached Australia’s Medicare Statistics portal in testing, exposing gaps in agentic AI governance. Discover the incident details and implications for cybersecurity.
-
Prompt Injection Threats to Autonomous AI Agents
Prompt injection has evolved into a structural threat for autonomous AI agents via indirect attacks and memory poisoning. Discover the risks, stakeholder impacts, and practical defenses…
-
OpenAI Launches Rogue AI Agent Reporting Portal
OpenAI introduces a reporting portal for rogue AI agents to help enterprises manage autonomous model risks. Learn how this impacts security, observability, and DevSecOps practices.
-
Enterprise AI Security: Fragmented Frameworks and Gaps
Navigate the crowded field of enterprise AI security frameworks from NIST, MITRE, and OWASP. Uncover practical gaps in LLM, RAG, and agent security for CISOs and…
-
AI Agents Run Malicious Code from Poisoned Git Repositories
New research shows autonomous AI agents like Claude and Grok can execute malware in tampered Git repos. Learn why zero-trust architecture is essential for safe agent…
-
AI Cyberattacks Warning: 100+ Leaders Urge Machine-Speed Defenses
OpenAI, Google, and 100+ AI firms warn the window to secure infrastructure from AI cyberattacks is closing. Discover why enterprises must pivot to AI-automated defenses now.
-
AI-to-AI Warfare: Cybersecurity Enters Machine-Speed Era
Major tech firms and agencies launch a defensive surge against AI-driven cyberattacks. Discover how AI copilots and secure-by-design mandates aim to counter machine-speed threats. Learn more.
-
Alabama Probes OpenAI Over Rogue AI Attack on Hugging Face
Alabama state authorities investigate OpenAI after a reported rogue AI cyberattack on Hugging Face. Learn the real implications for MLOps security and AI liability.
-
Zero Data Retention (ZDR) for Enterprise AI Adoption
Discover how Zero Data Retention from OpenAI, Anthropic, Azure, and AWS unlocks secure LLM use in finance, healthcare, and defense. Learn the compliance benefits and observability…