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
☆15Updated 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:
- ☆18Updated 8 months ago
- The most comprehensive and accurate LLM jailbreak attack benchmark by far☆21Updated 8 months ago
- A repo for LLM jailbreak☆14Updated 2 years ago
- Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers☆66Updated last year
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆368Updated 10 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆117Updated last year
- Q&A dataset for many-shot jailbreaking☆13Updated last year
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆53Updated 2 years ago
- ☆190Updated 2 years ago
- ☆113Updated 7 months ago
- Working Memory Attack on LLMs☆17Updated 6 months ago
- ☆26Updated last year
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆16Updated 9 months ago
- Whispers in the Machine: Confidentiality in Agentic Systems☆41Updated last week
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆149Updated 3 months ago
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆18Updated last year
- [ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability☆173Updated 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
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆70Updated last year
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆92Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆493Updated 8 months ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆20Updated last year
- This repository provides a benchmark for prompt injection attacks and defenses in LLMs☆361Updated last month
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆90Updated 7 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆156Updated last year
- Official implementation of the WASP web agent security benchmark☆60Updated 4 months ago
- [ACL24] Official Repo of Paper `ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs`☆90Updated 4 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆165Updated last year
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆73Updated 6 months ago
- ☆108Updated 2 weeks ago