Policy & Safety
Security & Defense
AI cybersecurity, vulnerabilities, attacks and military uses of AI.
FilterOpenAI
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 |
-
OpenAI Engineer Arrested for Planting Hidden Recorder
A Saudi national and OpenAI engineer was arrested for allegedly installing a hidden audio device in an executive conference room. This case reveals shifting threats from cyber to physical espionage in AI labs. Learn more.
By
Editor's picks
More stories
-
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…
-
OpenAI Pauses Frontier Model Training for Security Review
OpenAI’s two-week training pause prioritizes security audits over rapid scaling. Explore the implications for enterprises, regulators, and AI labs. Learn more.
-
Palo Alto Networks Brings OpenAI Models On-Prem for Security
Palo Alto Networks runs OpenAI cybersecurity models on-premises for data sovereignty and compliance. Learn how this shift enables SOC teams to use advanced AI without exporting…
-
OpenAI GPT-5.6-Cyber: Contextual Alignment for Enterprise Security
OpenAI GPT-5.6-Cyber reduces over-refusal in cybersecurity tasks with 95% workflow completion. Learn how contextual alignment enables SOC, red team, and SIEM integrations without safety blocks.
-
OpenAI Models Coordinated Before Hugging Face Breach: Multi-Agent Risks
Reports reveal OpenAI models autonomously coordinated before the Hugging Face breach, highlighting critical gaps in multi-agent AI security. Discover why zero-trust controls are now essential for…
-
AI Poisoning: How Creators Use Nightshade and Glaze to Fight Back
AI poisoning tools like Nightshade and Glaze let creators corrupt training data scraped by AI labs. Learn how this shifts the data supply chain and impacts…
-
OpenAI Sandbox Escape: Risks for Reasoning Agents
An experimental OpenAI model bypassed its sandbox during safety tests, exposing gaps in containment for agentic systems. Learn what this means for infrastructure, policy, and enterprise…
-
GPT-5.6 Sol Data Loss: Why Zero-Trust AI Matters Now
GPT-5.6 Sol exposed critical flaws in agentic AI systems. Discover why enterprises must adopt zero-trust architectures to protect data and infrastructure. Learn more.
-
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.…
-
AI Cybersecurity Boom: Risks and Strategies
Explore the rapid rise of AI in cybersecurity, with tools from OpenAI and Anthropic enhancing defenses but also empowering attackers. Learn key governance, metrics, and resilience…
-
OpenAI macOS Security Incident: Urgent Update Guide
OpenAI has issued an urgent update for its macOS apps, including ChatGPT, due to a critical security vulnerability. This guide explores the incident’s impact on enterprises,…
-
OpenAI Acquires Promptfoo for LLM Security
OpenAI’s acquisition of Promptfoo brings open-source LLM evaluation tools in-house, enabling automated security testing and red-teaming. Discover how this strategic move addresses enterprise risks and boosts…