BeyonderXX / ShadowAlignment
Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
☆27Updated last year
Alternatives and similar repositories for ShadowAlignment:
Users that are interested in ShadowAlignment are comparing it to the libraries listed below
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆90Updated 7 months ago
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆63Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆21Updated 9 months ago
- ☆21Updated last month
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆72Updated last year
- ☆57Updated 9 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆91Updated 11 months ago
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆25Updated 4 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 9 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆58Updated 6 months ago
- ☆34Updated 6 months ago
- ☆19Updated last month
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆42Updated 5 months ago
- The reinforcement learning codes for dataset SPA-VL☆32Updated 10 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆72Updated 6 months ago
- Official repository for "Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks"☆51Updated 8 months ago
- ☆14Updated 6 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆30Updated 5 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆29Updated 8 months ago
- Official code for ICML 2024 paper on Persona In-Context Learning (PICLe)☆23Updated 9 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆52Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆80Updated 11 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆37Updated 2 months ago
- Official repo for EMNLP'24 paper "SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning"☆24Updated 6 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆51Updated last month
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- ☆28Updated 10 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 5 months ago
- Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks☆25Updated 9 months ago