Policy & Safety
Security & Defense – Page 10
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 Agents in Browsers: Security & Legal Risks
Discover the hidden security threats of AI agents in browsers like Edge and Arc, including prompt injection and session leaks. Learn about the underreported legal risks…
-
First AI-Orchestrated Cyber Espionage Campaign Exposed
Explore the first documented case of an AI-orchestrated cyber espionage campaign using large language models like Anthropic’s Claude. This report details how AI autonomously handles reconnaissance…
-
Anthropic AI Hack: New Phase in Cyber Conflict
Anthropic’s revelation of a China-linked hacking attempt using its LLMs marks the start of AI-fueled cyber battles. Explore how this shifts attack strategies, challenges traditional defenses,…
-
Claude AI in Cyber Espionage: Anthropic’s Report
Explore Anthropic’s revelation of the first AI-orchestrated cyber espionage campaign using Claude, automating 90% of attacks, plus vulnerabilities like CVE-2025-54795 in Claude Code. Gain insights for…
-
Claude AI Cyberattack: Anthropic’s Analysis & Implications
Discover how Anthropic’s Claude AI was abused in the first fully orchestrated cyber-espionage attack. Explore the implications for AI security, affected stakeholders, and the shift to…
-
ChatGPT Leaks: AI Security Risks and Data Containment
Discover how recent ChatGPT leaks exposed vulnerabilities in AI web-browsing and analytics, highlighting risks to enterprise security and the urgent need for data containment. Explore insights…
-
Prompt Injection: #1 OWASP Risk for AI Systems
Explore prompt injection, now the top OWASP threat to generative AI. Learn about direct and indirect attacks, stakeholder impacts, and mitigation strategies for secure LLM applications.…
-
AI-Industrialized Cybercrime: Threats and Insights
Discover how generative AI is fueling industrialized cybercrime, from automated phishing to agentic attacks. Explore NIST, NCSC reports on threats to AI systems and defenses for…
-
Is OpenAI Too Big to Fail? AI Infrastructure Risks
Explore the debate on whether OpenAI is too big to fail, examining its market dominance, supply chain vulnerabilities, and systemic impacts on businesses and regulators. Discover…
-
OpenAI Atlas Browser: AI Risks & Implications
Explore OpenAI’s Atlas browser, integrating ChatGPT for seamless AI-assisted browsing. Discover privacy concerns, security risks like prompt injection, and strategic impacts on users and enterprises. Learn…