#red-teaming
-
Automated Jailbreak Attacks: GCG, AutoDAN, PAIR, TAP
Four automated jailbreak generators compared: GCG, AutoDAN, PAIR and TAP, by model access, query budget, prompt readability and detection signature.
-
Promptfoo Alternatives for LLM Red Teaming
OpenAI announced its acquisition of Promptfoo in March 2026. The open-source LLM red team tools that stayed vendor-neutral, compared by scope and depth.
-
Prompt Injection vs Jailbreak: Two Different Attacks on LLMs
Prompt injection and jailbreak get conflated constantly, but they hit different layers and need different defenses. Here is how to tell them apart.
-
Best LLM Red Team Tools: Garak, PyRIT, and Promptfoo
The best LLM red team tools are compared across attack coverage, multi-turn depth, CI integration, strengths, limitations, and ideal use cases.
-
LLM Jailbreak Techniques Explained: Practitioner's Taxonomy
A technical breakdown of LLM jailbreak techniques by attack category, from role-play bypasses to multilingual exploits and multi-turn escalation.
-
Many-Shot vs. Single-Shot Jailbreaks: Long-Context Risks
Single-shot jailbreaks compress the entire attack into one prompt; many-shot jailbreaks exploit the model's in-context learning.
-
Jailbreak Detection-Evasion Arms Race: How Attackers Adapt
Jailbreak detection and evasion form an arms race in which attackers probe classifier boundaries and defenders use layered safeguards.
-
LLM Jailbreak Taxonomy 2026: How the Techniques Cluster
Six years of jailbreak research has produced a messy literature. This taxonomy organizes working techniques by the behavioral property each one exploits.