xyq7 / GradSafe
Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"
☆40Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for GradSafe
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆43Updated 11 months ago
- ☆66Updated 11 months ago
- JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and further assess …☆35Updated 4 months ago
- The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"☆31Updated 6 months ago
- SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors☆33Updated 4 months ago
- ☆39Updated last week
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆28Updated last month
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆67Updated 11 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆21Updated 4 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆42Updated 3 months ago
- Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆85Updated 6 months ago
- Accepted by ECCV 2024☆73Updated 3 weeks ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆44Updated last month
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆83Updated 5 months ago
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆42Updated 4 months ago
- A curated list of trustworthy Generative AI papers. Daily updating...☆67Updated 2 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆52Updated 3 weeks ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆78Updated 5 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆23Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆32Updated 2 weeks ago
- ☆38Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆46Updated 3 months ago
- Official Code for "Baseline Defenses for Adversarial Attacks Against Aligned Language Models"☆20Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆28Updated 2 weeks ago
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆58Updated last month
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆120Updated 6 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆70Updated 2 months ago
- Towards Safe LLM with our simple-yet-highly-effective Intention Analysis Prompting☆12Updated 7 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆45Updated 2 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆51Updated 3 months ago