Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #ai-security-news 7
- #weekly-digest 7
- #ai-security 5
- #cve 3
- #detection 3
- #llm-security 3
- #owasp 3
- #policy 3
- #prompt-injection 3
- #email-security 2
- #generative-ai 2
- #phishing 2
- #supply-chain 2
- #2025 1
- #adversarial-attacks 1
- #adversarial-examples 1
- #ai-attacks 1
- #ai-detection 1
- #appsec 1
- #certification 1
- #deep-learning 1
- #deepfakes 1
- #frameworks 1
- #governance 1
- #incidents 1
- #jailbreak 1
- #litellm 1
- #machine-learning-security 1
- #media-forensics 1
- #mitre-atlas 1
- #model-robustness 1
- #model-unlearning 1
- #multimodal 1
- #nist-ai-rmf 1
- #rag-security 1
- #regulatory 1
- #retrospective 1
- #social-engineering 1
- #stylometry 1
- #synthetic-media 1
- #threat-intelligence 1
- #trends 1
- #vllm 1
- #year-in-review 1
Categories
Weekly Digest 6 posts
- AI Security Week: May 18, 2026A self-propagating npm and PyPI worm sweeps up AI SDKs including Mistral AI and Guardrails AI, two critical RCE classes in vLLM, and CAISI's testing deals.
- AI Security Week: May 13, 2026A pre-auth SQL injection in LiteLLM enters CISA's KEV catalog, the EU provisionally agrees to reshape the AI Act, and injection reaches code execution.
- AI Security Week: May 6, 2026Analysis and commentary on provider usage policy for security research, image-embedded prompt injection, and the ML library flaw classes worth watching.
- AI Security Week: May 5, 2026Analysis and commentary on weak machine-unlearning guarantees, the RAG exposure misconfiguration class, and ENISA-aligned AI incident response practice.
- AI Security Week: May 4, 2026Analysis and commentary on transfer-resistant adversarial examples, the typosquat class against ML packaging, and NIST AI RMF adoption in practice.
- AI Security Week: May 3, 2026Analysis and commentary on Anthropic's safety-research posture, the recurring path-traversal class in LLM middleware, and EU AI Act enforcement signals.
Detection 3 posts
- How to Tell If an Email Was Written by AIHow to tell if an email was written by AI: the stylometric tells that survive, why AI-text detectors misfire, and the checks that matter more.
- How to Detect AI-Generated Phishing: Signals and ChecksHow to detect AI-generated phishing once bad grammar stops being a tell: the stylometric signals, sender-verification checks, and controls that still hold.
- Deepfake Detection Methods 2026: What Works and What FailsA technical survey of deepfake detection methods in 2026: foundation-model ensembles, spectral forensics, multimodal pipelines, and the accuracy gap.
AI Security 2 posts
- Adversarial Examples in Machine Learning ExplainedAdversarial examples in machine learning explained: what they are, how the Fast Gradient Sign Method works, and which defenses actually hold up.
- What Is a Prompt Injection Attack? Types and DefensesA prompt injection attack manipulates an LLM's instruction-following logic to override intended behavior. Ranked OWASP LLM01, it affects chatbots and agents.
Frameworks 2 posts
- AI Security Frameworks Compared: NIST, OWASP, ATLASAI security frameworks compared: what NIST AI RMF, the OWASP LLM Top 10, MITRE ATLAS, and ISO/IEC 42001 each cover, and how they fit together.
- OWASP Top 10 for LLM Applications: The 2025 List ExplainedA practitioner walkthrough of the OWASP Top 10 for LLM Applications, covering all ten risk categories and what changed from the first 2023 release.