Policy & Safety
Security & Defense – Page 5
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
-
Indirect Prompt Injection: Browser AI Security Risks
Indirect prompt injection allows attackers to hijack browser AI agents and steal session data. Discover the risks for Edge, Arc, Brave and enterprise compliance teams.
-
Autonomous AI Agents: Enterprise Governance and Security Needs
Autonomous AI agents move beyond chat tools to action. Discover why governance, evaluation, and controls are the real barriers to production deployment for enterprises. Learn more.
-
Agentic Zero Trust: Securing Autonomous AI Agents
Explore why Agentic Zero Trust is essential for AI agents executing real tasks. Learn about biometric security, human oversight, and enterprise controls to mitigate risks. Discover…
-
Audio Prompt Injection: Hidden Risks for AI Voice Agents
Attackers can now embed invisible commands in podcasts and videos using ultrasonic carriers. Discover how this affects autonomous AI agents and the controls needed to secure…
-
NVIDIA Verified Agent Skills: Secure AI Agent Governance
NVIDIA Verified Agent Skills applies zero-trust and least-privilege controls to limit AI agent actions. Map every operation to SOC 2, HIPAA, and ISO 27001 compliance with…
-
OpenAI Daybreak Initiative: AI Cybersecurity
Discover OpenAI’s Daybreak Initiative powered by Codex Security LLMs. Automates vulnerability triage, generates patch tests, and validates fixes to slash MTTR. Integrates with SIEM, EDR, CI/CD.…
-
Vibe-Coding and Shadow AI Security Crisis Explained
Explore the emerging Shadow AI security crisis driven by vibe-coding apps built with AI tools. Learn how insecure defaults lead to data exposures and discover strategies…
-
AI in Cyberattacks: Dragos Reveals LLM Misuse
Discover how threat actors are leveraging commercial LLMs like GPT for planning attacks on critical infrastructure. Learn the impacts on OT sectors and essential defensive strategies…
-
Claude RCE Vulnerability: Key AI Safety Insights
Discover the recent one-click RCE vulnerability in Anthropic’s Claude, its implications for AI agents, and why it demands secure-by-default practices. Explore enterprise risks, stakeholder impacts, and…
-
Anthropic AI Safety vs National Security: Hegseth Clash
Explore the heated debate between Pete Hegseth and Anthropic’s Dario Amodei over AI safety policies restricting military use. Analyze impacts on defense, ethics, and the industry.…
-
Perplexity AI Forces Phone 2FA: Backlash and Account Locks
Perplexity AI’s mandatory phone-based 2FA for Pro subscribers has locked out users and sparked backlash. Explore the reasons, impacts on stakeholders, and implications for AI security.…
-
MYTHOS AI Threat: Cybersecurity Risks in India
Explore the unverified MYTHOS cybersecurity campaign targeting LLMs like Claude in Indian enterprises. Learn its implications for AI security, stakeholder impacts, and steps to build resilient…