AI Attacks
Home Posts Topics
☰
Plan Builder Tools Glossary Resources About
Offensive Sec network
Adversarial ML AI Sec JailbreakDB Jailbreaks FYI ML CVEs
Clean isometric vector illustration explaining website purpose and meta tags functionality
site

What this site is for

AI Attacks covers offensive AI security from a working practitioner's perspective. Here's what we publish.

By AI Attacks Editorial · · 7 min read

AI Attacks exists to cover offensive AI security with the same rigor a working AI red teamer would expect — and the same honesty about what does and doesn’t land in production.

What we publish:

Technical writeups of working attacks. Prompt injection variants, jailbreak techniques and the model behaviors they exploit, indirect injection through retrieved content, multi-modal attack chains, agent and tool-use abuse. Where possible, reproducible PoCs against open models. Closed models get attack patterns and behavioral analysis.

Adversarial ML, applied. Membership inference, model extraction, evasion attacks, training-data extraction, backdoors — focused on what’s exploitable in deployed systems, not theoretical bounds.

Red team methodology. Scoping AI engagements, building attack libraries, communicating findings to a model team that doesn’t speak security and a security team that doesn’t speak ML.

Tooling reviews. Honest takes on the offensive AI security tooling landscape — Garak, PyRIT, promptmap, the LLM-specific scanners — and what each is actually good for.

What we don’t publish:

  • Press release rewrites
  • Listicles
  • Anything we can’t source to primary material

Bylines are pseudonymous. The work is the point. Tips, attack reports, and corrections to the editor.

Real content starts shortly.

#meta
Subscribe

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.

Related

Isometric vector illustration representing owasp top 10 llm explained
LLM Security

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.
Diagram of evasion payload evading malware detector while preserving malicious functionality.
adversarial-ml

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.
Illustration of split-view poisoning injecting malicious content into web-scale training datasets.
adversarial-ml

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.

Comments