AI Sec
AI Sec ai security · sourced notes updated 2026-08-27
// archive

Sourced notes on AI red teaming.

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.

Enter the archive →

Latest entries

// index10 of 35 entries

GPT Security: Attack Surfaces and Production Controls

red-team

ChatGPT Exploits: Injection, Memory Hijack, Plugin Abuse

prompt-injection

Insecure Output Handling: LLM05:2025 Attacks and Defenses

red-team

Many-Shot Jailbreaking: How Long Context Breaks Alignment

jailbreak

System Prompt Injection: How Extraction and Override Attacks Work

prompt-injection

LLM Security Vulnerabilities: What Actually Gets Exploited

red-team

GPT-Red: What OpenAI's Prompt-Injection Attacker Proves

red-team

LLM Attack Taxonomy: Prompt Injection, Jailbreaks, Agent Hijack

red-team

AI Red Team: Methodology, Tooling, and Attack Surface

red-team

The Adversarial ML Attack Taxonomy: A Red Teamer's Reference

red-team

Independent, specialist, and free to read

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

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.