git-disl / BoosterLinks
This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation" (ICLR2025 Oral).
☆28Updated 3 months ago
Alternatives and similar repositories for Booster
Users that are interested in Booster are comparing it to the libraries listed below
Sorting:
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆44Updated 7 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆23Updated 10 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆19Updated 4 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆137Updated 2 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆80Updated 3 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆23Updated 2 weeks ago
- Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as …☆65Updated this week
- Official repository for "Safety in Large Reasoning Models: A Survey" - Exploring safety risks, attacks, and defenses for Large Reasoning …☆60Updated last month
- A survey on harmful fine-tuning attack for large language model☆192Updated 2 weeks ago
- ☆22Updated 4 months ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆30Updated 3 months ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆47Updated 8 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆26Updated 9 months ago
- [ICLR 2024] Towards Elminating Hard Label Constraints in Gradient Inverision Attacks☆13Updated last year
- Github repo for NeurIPS 2024 paper "Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models"☆15Updated 9 months ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆10Updated 8 months ago
- [ACL 2025] Data and Code for Paper VLSBench: Unveiling Visual Leakage in Multimodal Safety☆47Updated last month
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆42Updated 8 months ago
- "In-Context Unlearning: Language Models as Few Shot Unlearners". Martin Pawelczyk, Seth Neel* and Himabindu Lakkaraju*; ICML 2024.☆27Updated last year
- Accepted by ECCV 2024☆142Updated 9 months ago
- Official codebase for "STAIR: Improving Safety Alignment with Introspective Reasoning"☆56Updated 4 months ago
- ☆60Updated last year
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆73Updated 5 months ago
- ☆21Updated 3 months ago
- An implementation for MLLM oversensitivity evaluation☆13Updated 8 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆56Updated 4 months ago
- ☆41Updated 9 months ago
- ☆52Updated 3 months ago
- ☆31Updated last month
- To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models☆31Updated last month