jiaxiaojunQAQ / I-GCG
Improved techniques for optimization-based jailbreaking on large language models
☆64Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for I-GCG
- [arXiv 2024] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆91Updated last week
- [CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models☆106Updated last month
- Improving fast adversarial training with prior-guided knowledge (TPAMI2024)☆36Updated 7 months ago
- [ICML22] "Revisiting and Advancing Fast Adversarial Training through the Lens of Bi-level Optimization" by Yihua Zhang*, Guanhua Zhang*, …☆73Updated 2 years ago
- Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging (TIFS2024)☆35Updated 5 months ago
- [CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models☆153Updated 7 months ago
- Practical Detection of Trojan Neural Networks☆156Updated 4 years ago
- [ICLR 2023] Official Tensorflow implementation of "Distributionally Robust Post-hoc Classifiers under Prior Shifts"☆39Updated 9 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆12Updated 3 months ago
- ☆73Updated last year
- ☆67Updated this week
- Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, data…☆362Updated this week
- Code for Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack☆28Updated 2 weeks ago
- [NeurIPS22] "Advancing Model Pruning via Bi-level Optimization" by Yihua Zhang*, Yuguang Yao*, Parikshit Ram, Pu Zhao, Tianlong Chen, Min…☆141Updated last year
- A comprehensive collection of resources focused on addressing and understanding hallucination phenomena in MLLMs.☆38Updated 6 months ago
- CVPR 2022 Workshop Robust Classification☆94Updated 2 years ago
- Benchmarking LLMs via Uncertainty Quantification☆221Updated 9 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆48Updated 3 months ago
- Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet, CVPR2021 安全AI挑战者计划第六期：…☆54Updated 3 years ago
- [ACL 2024] CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and …☆111Updated 3 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆14Updated last month
- [ICML2022 Long Talk] Official Pytorch implementation of "To Smooth or Not? When Label Smoothing Meets Noisy Labels"☆116Updated 2 years ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆29Updated last month
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 4 months ago
- We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that …☆117Updated last year
- ☆25Updated 4 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆15Updated last month
- ☆53Updated last year
- All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks☆15Updated 7 months ago
- 🚀 [NeurIPS24] Make Vision Matter in Visual-Question-Answering (VQA)! Introducing NaturalBench, a vision-centric VQA benchmark (NeurIPS'2…☆66Updated 2 weeks ago