Practitioner-grade AI red team techniques and tooling.
Working AI red team techniques from the practitioner trenches. Attack patterns, tooling, scoping methodology, and reproducible PoCs against deployed LLMs and agents — sourced from real engagements and primary research, not vendor decks.
OWASP Top 10 LLM Explained: Every Entry, What It Means, and What to Fix
The OWASP Top 10 for LLM Applications 2025 is the canonical vulnerability taxonomy for production AI systems. Here is every entry, what it means in practice, and the highest-return mitigations.
Featured
Evasion Attacks on Production Classifiers: Malware, Spam, and Fraud
Deployed ML classifiers in malware, spam, and fraud detection face evasion attacks where the attacker has a clear payoff. How the attacks work against real systems, why black-box transfer is the practical threat, and what actually raises the cost of evasion.
Poisoning Web-Scale Training Sets: Split-View and Frontrunning
You don't need to control a model's training pipeline to poison it — you only need to control content the crawler will fetch. How split-view and frontrunning poisoning work against web-scale datasets, and the integrity controls that defend the pipeline.
Adversarial Examples Against Vision Models in 2025
Where physical-world adversarial patches and digital attacks stand against modern vision models — what still works, what's been hardened, and where the research frontier is.
Recent
-
Adversarial Suffixes: A GCG Practitioner Guide
-
Jailbreaking Multimodal Models: Visual Prompt Injection Attacks
-
LLM Jailbreaking via Many-Shot Prompting
-
Model Extraction via Black-Box Query Attacks
-
Supply Chain Attacks on AI Models: Poisoning and Backdoors
-
LLM Context Window Poisoning
-
Model Inversion and Membership Inference: Extracting LLM Data
-
Indirect Prompt Injection in RAG Pipelines
Trusted by researchers across the AI security community
AI Attacks is part of a 26-site editorial network covering adversarial ML, AI governance, defensive tooling, and ops engineering — all open access.
AI Attacks — in your inbox
Practitioner-grade AI red team techniques and tooling. — delivered when there's something worth your inbox.
No spam. Unsubscribe anytime.