Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #llm-security 15
- #jailbreak 10
- #red-teaming 8
- #prompt-injection 4
- #taxonomy 3
- #adversarial-attacks 2
- #adversarial-testing 2
- #gcg 2
- #in-context-learning 2
- #adaptive-attacks 1
- #arms-race 1
- #autodan 1
- #automated-attacks 1
- #base64 1
- #behavioral-monitoring 1
- #benchmark 1
- #chatgpt 1
- #classifier 1
- #classifier-evasion 1
- #content-filter 1
- #content-filter-bypass 1
- #context-window 1
- #crescendo 1
- #cvd 1
- #dan 1
- #dan-prompt 1
- #defense 1
- #detection-evasion 1
- #encoding-attacks 1
- #evaluation 1
- #garak 1
- #gradient-attacks 1
- #guardrails 1
- #harmbench 1
- #input-filtering 1
- #jailbreak-detection 1
- #jailbreak-history 1
- #jailbreakbench 1
- #long-context 1
- #many-shot 1
- #many-shot-jailbreaking 1
- #multi-turn 1
- #obfuscation 1
- #openai 1
- #pair 1
- #persona 1
- #promptfoo 1
- #pyrit 1
- #research 1
- #research-ethics 1
- #responsible-disclosure 1
- #rlhf 1
- #roleplay-jailbreak 1
- #strongreject 1
- #tools 1
- #transferability 1
- #unicode 1
- #universal-suffix 1
- #vulnerability-disclosure 1
Categories
technique 8 posts
- Automated Jailbreak Attacks: GCG, AutoDAN, PAIR, TAPFour automated jailbreak generators compared: GCG, AutoDAN, PAIR and TAP, by model access, query budget, prompt readability and detection signature.
- Prompt Injection vs Jailbreak: Two Different Attacks on LLMsPrompt injection and jailbreak get conflated constantly, but they hit different layers and need different defenses. Here is how to tell them apart.
- LLM Jailbreak Techniques Explained: Practitioner's TaxonomyA technical breakdown of LLM jailbreak techniques by attack category, from role-play bypasses to multilingual exploits and multi-turn escalation.
- Crescendo Multi-Turn Jailbreaks: Why Defenses Miss ThemCrescendo multi-turn jailbreaks evade per-message defenses by exploiting conversation context, requiring session-level classification and monitoring.
- Encoding and Obfuscation Jailbreaks: The Filter-Model GapEncoding and obfuscation jailbreaks exploit representation gaps between content filters and LLMs; normalization and decoding can help detect them.
- Roleplay and Persona Jailbreaks: Why They Often FailRoleplay and persona jailbreaks such as DAN use fictional framing, but modern safety training blocks many variants on frontier models.
research 3 posts
- Jailbreak Testing: HarmBench, JailbreakBench, StrongREJECTHarmBench, JailbreakBench, and StrongREJECT show how behavior sets, attacker harnesses, judges, and target models shape attack success rates.
- Jailbreak Detection-Evasion Arms Race: How Attackers AdaptJailbreak 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 ClusterSix years of jailbreak research has produced a messy literature. This taxonomy organizes working techniques by the behavioral property each one exploits.
tools 2 posts
- Promptfoo Alternatives for LLM Red TeamingOpenAI announced its acquisition of Promptfoo in March 2026. The open-source LLM red team tools that stayed vendor-neutral, compared by scope and depth.
- Best LLM Red Team Tools: Garak, PyRIT, and PromptfooThe best LLM red team tools are compared across attack coverage, multi-turn depth, CI integration, strengths, limitations, and ideal use cases.