TrustAI-laboratory / Many-Shot-Jailbreaking-DemoLinks
Research on "Many-Shot Jailbreaking" in Large Language Models (LLMs). It unveils a novel technique capable of bypassing the safety mechanisms of LLMs, including those developed by Anthropic and other leading AI organizations. Resources
☆14Updated last year
Alternatives and similar repositories for Many-Shot-Jailbreaking-Demo
Users that are interested in Many-Shot-Jailbreaking-Demo are comparing it to the libraries listed below
Sorting:
- [Usenix Security 2025] Official repo of paper PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs☆16Updated 5 months ago
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆21Updated 7 months ago
- ☆17Updated 7 months ago
- A repo for LLM jailbreak☆14Updated 2 years ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆64Updated last year
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆115Updated last year
- Working Memory Attack on LLMs☆16Updated 5 months ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆41Updated 3 weeks ago
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆14Updated 7 months ago
- ☆187Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆357Updated 9 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆53Updated last year
- Can Large Language Models Solve Security Challenges? We test LLMs' ability to interact and break out of shell environments using the Over…☆13Updated 2 years ago
- ☆109Updated 6 months ago
- Q&A dataset for many-shot jailbreaking☆12Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆141Updated 2 months ago
- ☆25Updated last year
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆18Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆69Updated 5 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆87Updated 6 months ago
- [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`☆90Updated 2 months ago
- ☆153Updated last year
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Updated 11 months ago
- Jailbreak artifacts for JailbreakBench☆70Updated 11 months ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses☆318Updated this week
- Code to conduct an embedding attack on LLMs☆27Updated 9 months ago
- PAL: Proxy-Guided Black-Box Attack on Large Language Models☆55Updated last year
- A benchmark for evaluating the robustness of LLMs and defenses to indirect prompt injection attacks.☆87Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆91Updated last year