xyq7 / GradSafeLinks
Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"
☆60Updated 11 months ago
Alternatives and similar repositories for GradSafe
Users that are interested in GradSafe are comparing it to the libraries listed below
Sorting:
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆53Updated last year
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆52Updated last week
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Updated last year
- ☆104Updated 8 months ago
- [AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts☆173Updated 3 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆55Updated 8 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆154Updated 5 months ago
- ☆35Updated last year
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆58Updated last year
- Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873☆166Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆62Updated 7 months ago
- ☆109Updated last year
- ☆63Updated 6 months ago
- Fingerprint large language models☆41Updated last year
- Accepted by ECCV 2024☆158Updated 11 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆144Updated last year
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆71Updated 11 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆77Updated 5 months ago
- A survey on harmful fine-tuning attack for large language model☆212Updated this week
- ☆20Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆35Updated last year
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆91Updated last year
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆44Updated 10 months ago
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆63Updated 9 months ago
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆45Updated 2 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆97Updated 4 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
- An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)☆43Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆77Updated 8 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆57Updated last month