AI Sec
// AI Sec

Offensive AI security — prompt injection, jailbreaks, agent exploitation, red team writeups.

Practitioner-grade analysis of offensive AI security. Prompt injection, model jailbreaks, agent and tool-use exploitation, AI red team techniques, and adversarial ML — distilled from primary sources, not press releases.

Isometric vector diagram showing adversarial prompt text flowing into an LLM context window with red override arrows
// Featured entry

Prompt Hacking: A Practitioner's Taxonomy of LLM Attack Classes

Prompt hacking covers three distinct attack classes against LLMs: direct injection, indirect injection, and jailbreaking. Here is how each works, what distinguishes them, and what actually stops them.

Jun 1, 2026 [prompt-injection]

// All entries

Why trust us

Trusted by researchers across the AI security community

AI Sec is part of a 26-site editorial network covering adversarial ML, AI governance, defensive tooling, and ops engineering — all open access.

26
Sites in network
Across 6 topic clusters
400+
Expert articles
And growing daily
Daily
New content
Automated + editorial
Free
Always free to read
Newsletter included
Subscribe

AI Sec — in your inbox

Offensive AI security — prompt injection, jailbreaks, agent exploitation, red team writeups. — delivered when there's something worth your inbox.

No spam. Unsubscribe anytime.