git-disl / Virus
This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"
☆46Updated 2 months ago
Alternatives and similar repositories for Virus:
Users that are interested in Virus are comparing it to the libraries listed below
- Improving Your Model Ranking on Chatbot Arena by Vote Rigging☆20Updated 2 months ago
- ☆63Updated this week
- ☆24Updated last month
- [TMLR'24] This repository includes the official implementation our paper "FedConv: Enhancing Convolutional Neural Networks for Handling D…☆25Updated 11 months ago
- The official implementation of Preference Data Reward-Augmentation.☆17Updated 6 months ago
- [CCS 2024] "BadMerging: Backdoor Attacks Against Model Merging": official code implementation.☆27Updated 8 months ago
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆72Updated 3 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆63Updated last month
- Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation☆29Updated 2 months ago
- Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning☆46Updated 2 months ago
- [ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast☆99Updated last year
- ☆24Updated last month
- ☆75Updated 5 months ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆67Updated 3 months ago
- (CVPR 2025) Official implementation to DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation which outperforms SOTA…☆20Updated last month
- AISafetyLab: A comprehensive framework covering safety attack, defense, evaluation and paper list.☆119Updated 3 weeks ago
- Knowledge Unlearning for Large Language Models☆25Updated 3 weeks ago
- Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives☆68Updated last year
- ☆51Updated 5 months ago
- The code repository for the CURLoRA research paper. Stable LLM continual fine-tuning and catastrophic forgetting mitigation.☆43Updated 7 months ago
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆63Updated last month
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆59Updated 3 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆86Updated 2 weeks ago
- Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the original meta-context of visual misinformatio…☆38Updated this week
- Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]☆43Updated 11 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆21Updated 5 months ago
- A tool to assist in the interpretation of learned features in sparse autoencoders (in particular the four SAE's trained by Joseph Bloom o…☆19Updated 6 months ago
- [NeurIPS VLM workshop 2024] In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Underst…☆22Updated last month
- This repository contains the code for the paper: SirLLM: Streaming Infinite Retentive LLM☆57Updated 10 months ago