Policy & Safety
Security & Defense – Page 7
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
-
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…
-
Anthropic Secures $200M Defense Contract for Claude AI
Anthropic’s $200 million defense contract brings Claude models and Constitutional AI into national security, validating safety-focused tech for government use. Explore stakeholder impacts, ethical challenges, and…
-
PromptSpy: AI-Enhanced Android Malware Threat
Explore PromptSpy, the innovative Android spyware exploiting Google’s on-device Gemini LLM to intelligently steal sensitive data like passwords and 2FA codes. Learn its attack methods, impacts…
-
Pentagon-Anthropic Clash: AI Safety vs Military Needs
Explore the growing tension between the Pentagon and Anthropic over Claude AI’s safety restrictions limiting DoD operations. Discover implications for defense AI adoption and vendor strategies.…
-
AI Model Extraction: Gemini Hack Insights
Explore the real threat behind hackers targeting Google’s Gemini API: not jailbreaks, but black-box model extraction to clone AI models. Understand impacts on AI vendors, security…
-
Pentagon Eyes Anthropic as AI Supply Chain Risk
The Pentagon is considering designating Anthropic’s AI models as a supply chain risk, impacting national security and AI vendors. Explore implications for transparency, compliance, and the…