Skip to content
snailsploit[$]Adversarial · Research
jailbreaking · hub
5 writeups · updated 2026.05

Jailbreaking.

Concrete bypass writeups and a complete technical taxonomy of jailbreak categories — from role hijacking and multi-turn escalation to context inheritance, encoding exploits, and chain-of-thought abuse. Each entry is a working bypass plus the structural reason it works.

2026-03-10
LLM Jailbreak Techniques: A Technical Taxonomy
Complete taxonomy of LLM jailbreak methods — role hijacking, multi-turn escalation, context manipulation, encoding exploits, and chain-of-thought abuse.
jailbreaking
2026-01-06
Memory Manipulation: AI Context Poisoning
How attackers poison AI context windows and memory systems to compromise future interactions. Persistent manipulation techniques and defense strategies.
jailbreaking
2025-01-04
Context Inheritance Exploit
Jailbroken states persist across GPT sessions through context inheritance. Explore this novel attack vector, its persistence mechanics, and defense gaps.
jailbreaking
2024-11-19
Is AI Inherently Vulnerable? An Offensive…
Are large language models inherently vulnerable? Examining the fundamental security limitations of LLMs and why adversarial manipulation remains unsolvable.
jailbreaking
2024-05-27
ChatGPT Jailbreak via Context Manipulation
Step-by-step walkthrough of jailbreaking ChatGPT using context manipulation and social awareness techniques. Original research and methodology breakdown.
jailbreaking
More research
all research →wiki →cves →