jiah-li / magicLinks
The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.
☆9Updated 5 months ago
Alternatives and similar repositories for magic
Users that are interested in magic are comparing it to the libraries listed below
Sorting:
- ☆14Updated 7 months ago
- ☆41Updated 8 months ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆17Updated 7 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆20Updated 10 months ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆16Updated last year
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆15Updated 4 months ago
- ☆21Updated 4 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year
- Submission Guide + Discussion Board for AI Singapore Global Challenge for Safe and Secure LLMs (Track 1A).☆16Updated 11 months ago
- ☆30Updated 11 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆24Updated 10 months ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆17Updated 2 weeks ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆61Updated 4 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 9 months ago
- ☆46Updated 2 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆26Updated 8 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆27Updated 10 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated last week
- [NeurIPS 2024] Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling☆28Updated 6 months ago
- ☆20Updated 2 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 10 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆49Updated last year
- The reinforcement learning codes for dataset SPA-VL☆33Updated 11 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆53Updated 9 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆73Updated last year
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆15Updated 5 months ago
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆12Updated last month
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆54Updated last year
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 10 months ago