Topic
AI Security
Security of and threats from AI / ML systems.
850
Stories tagged
20
Showing
§
On AI Security
Every story tagged with this topic, organised by desk.
Security1 story
Threat Intel1 story
AI Security11 stories
- Hugging Face warns an autonomous AI agent hacked its network20 Jul
- Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking20 Jul
- Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior20 Jul
- Poison to Detect: Detection of Targeted Overfitting in Federated Learning20 Jul
- Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation20 Jul
- Code-Poisoning Property Inference Attacks20 Jul
- Natural Backdoor Attacks on Speech Recognition Models20 Jul
- Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs20 Jul
- Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization20 Jul
- Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents20 Jul
- From Neural Intent to Cryptographic Authorization: Governing Agentic Workflows20 Jul
Vulnerabilities3 stories
Research3 stories