Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models
☆34Oct 19, 2023Updated 2 years ago
Alternatives and similar repositories for ShadowAlignment
Users that are interested in ShadowAlignment are comparing it to the libraries listed below
Sorting:
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆90May 2, 2025Updated 10 months ago
- ☆14Feb 26, 2025Updated last year
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆341Feb 23, 2024Updated 2 years ago
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated last year
- This is the code repo for the paper <UTC-IE: A Unified Token-pair Classification Architecture for Information Extraction>☆15Aug 10, 2023Updated 2 years ago
- Using conversational games to evaluate powerful LLMs☆18Sep 3, 2023Updated 2 years ago
- Official implementation for "HuRef: HUman-REadable Fingerprint for Large Language Models" (NeurIPS2024)☆15Jun 17, 2025Updated 8 months ago
- Source code of paper “A Novel Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation”☆16Nov 25, 2021Updated 4 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆20Aug 10, 2024Updated last year
- ☆37Jun 25, 2025Updated 8 months ago
- Defending Against Backdoor Attacks Using Robust Covariance Estimation☆22Jul 12, 2021Updated 4 years ago
- Code of Robust Lottery Tickets for Pre-trained Language Models (ACL2022)☆20Jul 18, 2022Updated 3 years ago
- ☆25Jun 23, 2021Updated 4 years ago
- ☆25Apr 16, 2021Updated 4 years ago
- OpenEA是一个基于知识图谱嵌入的开源实体融合工具，由南京大学提供。☆25Jul 31, 2021Updated 4 years ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆32Jul 11, 2022Updated 3 years ago
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆69Feb 27, 2024Updated 2 years ago
- Official repository of the paper: Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code (Findings of EACL …☆12Feb 11, 2026Updated 2 weeks ago
- ☆27Jun 5, 2023Updated 2 years ago
- The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.☆38Sep 8, 2024Updated last year
- Panda Guard is designed for researching jailbreak attacks, defenses, and evaluation algorithms for large language models (LLMs).☆64Jan 19, 2026Updated last month
- A re-implementation of the "Red Teaming Language Models with Language Models" paper by Perez et al., 2022☆35Oct 9, 2023Updated 2 years ago
- ☆33Jan 8, 2021Updated 5 years ago
- ☆12May 6, 2022Updated 3 years ago
- Dynamic, high-resolution poverty measurement in data-scarce environments☆10Dec 8, 2024Updated last year
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Jul 19, 2024Updated last year
- [ACL 23] CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors☆40Dec 14, 2025Updated 2 months ago
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆172Feb 20, 2024Updated 2 years ago
- Code for experiments on self-prediction as a way to measure introspection in LLMs☆16Dec 10, 2024Updated last year
- [IEEE TIP] Offical implementation for the work "BadCM: Invisible Backdoor Attack against Cross-Modal Learning".☆14Aug 30, 2024Updated last year
- Official Implementation of "Learning to Refuse: Towards Mitigating Privacy Risks in LLMs"☆10Dec 13, 2024Updated last year
- Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning☆30Sep 29, 2025Updated 5 months ago
- ☆11Oct 30, 2024Updated last year
- This is code for the EMNLP 2022 Paper "UniRPG: Unified Discrete Reasoning over Table and Text as Program Generation".☆10Apr 30, 2023Updated 2 years ago
- MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols☆16Nov 19, 2025Updated 3 months ago
- [NDSS 2025] Official code for our paper "Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Wate…☆45Nov 5, 2024Updated last year
- ☆11Dec 9, 2018Updated 7 years ago
- ☆12Jun 11, 2025Updated 8 months ago
- TOD-Flow: Modeling the Structure of Task-Oriented Dialogues☆13Feb 7, 2024Updated 2 years ago