AI Attacks
AI Attacks attack research · no vendor filter updated 2026-08-21
// archive

Every model has an attack surface.

AI attack techniques against deployed LLMs and agents: jailbreaks, prompt injection, model extraction, evasion, and data poisoning. Every technique is documented from published research, disclosed incidents, and vendor documentation, with the source named so you can check it.

Enter the archive →

Latest entries

// index10 of 21 entries

How Indirect Prompt Injection Works

Attack Techniques

LLM Jailbreak Defenses: Why Static Filters Fail

Defense

LLM Jailbreak Examples: 10 Documented Patterns

Attack Techniques

Prompt Injection vs Jailbreak: How They Differ and Why It Matters

Explainer

How to Detect Prompt Injection: Four Approaches Ranked

Defense

Adversarial Examples Explained Simply: How Pixels Fool a Model

Explainer

OWASP Top 10 LLM Explained: Every Entry and What to Fix

LLM Security

Evasion Attacks on Production Classifiers: Malware, Spam, Fraud

Adversarial ML

Poisoning Web-Scale Training Sets: Split-View and Frontrunning

Adversarial ML

Adversarial Examples Against Vision Models in 2026

Adversarial ML

Start here

The reference pages on this site, independent of publication date. Each one is sourced to published research and updated as the technique or the defense against it moves.

Independent, specialist, and free to read

AI Attacks publishes focused, sourced guides on a single topic. No paywall, no account, no ad tracking.

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.