Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #ai-security-news 12
- #weekly-digest 12
- #policy 5
- #owasp 4
- #supply-chain 4
- #ai-security 3
- #cve 3
- #agent-security 2
- #atlas 2
- #jailbreak 2
- #llm-security 2
- #prompt-injection 2
- #rag-security 2
- #2025 1
- #ai attacks 1
- #appsec 1
- #certification 1
- #generative ai 1
- #incidents 1
- #litellm 1
- #llm security 1
- #llm-top-10 1
- #model-extraction 1
- #model-unlearning 1
- #multimodal 1
- #nist 1
- #offensive-ai 1
- #phishing 1
- #practitioner 1
- #prompt injection 1
- #regulatory 1
- #retrospective 1
- #risk-management 1
- #threat-intel 1
- #threat-intelligence 1
- #trends 1
- #vllm 1
- #year-in-review 1
Categories
digest 11 posts
- AI Security Week: May 22, 2026Google says it caught attackers using an LLM to find a zero-day, peer-reviewed research shows reasoning models can autonomously jailbreak other models
- AI Security Week: May 18, 2026A self-propagating npm/PyPI worm sweeps up AI SDKs including Mistral AI and Guardrails AI, two critical RCE classes in the vLLM inference server, and the
- AI Security Week: May 13, 2026A critical pre-auth SQL injection in LiteLLM lands in CISA's KEV catalog, the EU reaches a provisional deal to delay and reshape the AI Act, and Microsoft
- AI Security Week: May 10, 2026Analysis and commentary: training-data poisoning as a durable class, ATLAS as a finding taxonomy, red-teaming through the data channel, and the EU AI
- AI Security Week: May 9, 2026Analysis and commentary: RAG retrieval as an injection channel, insecure output handling as the under-built control, the OWASP LLM Top 10 as an
- AI Security Week: May 8, 2026Analysis and commentary: the NIST AI RMF and its Generative AI Profile as a control map, the model/data supply-chain compromise class, why model
analysis 2 posts
- Understanding the OWASP LLM Top 10: What Matters MostOWASP published the LLM Top 10 in 2023 and updated it in 2025. The list is useful but requires interpretation.
- AI Security Year in Review: 2025The five most consequential AI security developments of 2025: the shift from theoretical to operational attacks, the supply chain compromise wave