Policy & Safety
Security & Defense – Page 9
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
-
Indirect Prompt Injection Attacks on AI Browsers
Discover emerging indirect prompt injection attacks targeting AI browsers like Microsoft Edge and Arc. Learn how hidden commands in web content, images, and URLs can hijack…
-
OpenAI Mixpanel Breach: AI Supply Chain Security Risks
Explore the OpenAI data breach via Mixpanel, exposing business customer metadata. Learn about supply-chain attacks in AI, stakeholder impacts, and strategies for enhancing security in the…
-
OpenAI Mixpanel Breach: SaaS Supply Chain Risks in AI
A data breach at Mixpanel exposed OpenAI API customer metadata, highlighting vulnerabilities in the AI SaaS supply chain. Discover impacts, stakeholder risks, and strategies for zero-trust…
-
OpenAI Data Exposure: Risks in AI Supply-Chain Security
Explore the OpenAI data exposure via Mixpanel breach, affecting API customers with leaked metadata. Discover impacts on developers, lessons in supply-chain security, and why data minimization…
-
Anthropic Disrupts First AI Cyber Espionage Campaign
Anthropic has uncovered and stopped the GTG-1002 incident, the first large-scale agentic AI cyber espionage attack. This analysis covers the tactics used, impacts on security teams…
-
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.…