jiaxiaojunQAQ / I-GCGLinks
Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)
☆125Updated 4 months ago
Alternatives and similar repositories for I-GCG
Users that are interested in I-GCG are comparing it to the libraries listed below
Sorting:
- [CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models☆134Updated last month
- [ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".☆131Updated 3 months ago
- AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.☆200Updated this week
- Code for NeurIPS 2024 Paper "Fight Back Against Jailbreaking via Prompt Adversarial Tuning"☆16Updated 3 months ago
- [CVPR2024] MMA-Diffusion: MultiModal Attack on Diffusion Models☆168Updated 2 months ago
- Code for Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks (TIFS2024)☆13Updated last year
- ☆30Updated 3 months ago
- Improving fast adversarial training with prior-guided knowledge (TPAMI2024)☆41Updated last year
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆27Updated 10 months ago
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment☆23Updated 3 months ago
- A curated list of resources dedicated to the safety of Large Vision-Language Models. This repository aligns with our survey titled A Surv…☆133Updated last month
- ☆50Updated last year
- ☆58Updated 5 months ago
- ☆47Updated last year
- ☆59Updated 3 months ago
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆22Updated last year
- YiJian-Comunity: a full-process automated large model safety evaluation tool designed for academic research☆114Updated 10 months ago
- Code for ACM MM2024 paper: White-box Multimodal Jailbreaks Against Large Vision-Language Models☆30Updated 8 months ago
- Code for "When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search" (NeurIPS 2024)☆10Updated 10 months ago
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆61Updated 8 months ago
- A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models☆216Updated 2 weeks ago
- ☆102Updated last year
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆69Updated this week
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆164Updated 2 months ago
- Welcome to the official repository for Siren, a project aimed at understanding and mitigating harmful behaviors in large language models …☆11Updated 7 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆73Updated 3 months ago
- Emoji Attack [ICML 2025]☆24Updated last month
- Official Code for ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users (NeurIPS 2024)☆16Updated 10 months ago
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆43Updated 9 months ago
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated 3 months ago