AI Sec ai security · field notes rev.2026.06
// Recently indexed archive
Field notes from the AI red team.
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
// index34 entries
LLM Attack Taxonomy: Prompt Injection, Agent Hijack, and What's Hitting Production
red-teamPrompt Injection Examples: Attack Payloads by Class
prompt-injectionLLM Bypass Techniques: Attack Families, PoC Patterns, and Why Guardrails Keep Failing
jailbreakAI Red Team: Methodology, Tooling, and the Attack Surface That Actually Matters
red-teamPrompt Hacking: A Practitioner's Taxonomy of LLM Attack Classes
prompt-injectionThe Adversarial ML Attack Taxonomy: A Red Teamer's Reference
red-teamAI Red Team Engagement Methodology: Scoping to Reporting
red-teamThe Audit Gap: Why Red-Teaming Can't Certify Governance Claims
red-teamPrompt Injection in 2025: OpenAI vs. Broken Defenses
prompt-injectionLLM Prompt Injection: From Instruction Override to Agent Takeover
prompt-injection
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.