thunlp / Advbench
Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP".
☆32Updated last year
Related projects: ⓘ
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆61Updated 4 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆64Updated 2 weeks ago
- ☆32Updated 11 months ago
- ☆37Updated 10 months ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆76Updated 6 months ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆26Updated 2 years ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆79Updated 3 months ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆26Updated last year
- ☆47Updated last year
- ☆23Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆59Updated last year
- Multilingual safety benchmark for Large Language Models☆21Updated 2 weeks ago
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆55Updated 8 months ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆33Updated 3 weeks ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆22Updated 11 months ago
- ☆32Updated 10 months ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆36Updated 3 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆77Updated 4 months ago
- Official code for the paper: Evaluating Copyright Takedown Methods for Language Models☆14Updated 2 months ago
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆18Updated last year
- ☆101Updated last year
- Restore safety in fine-tuned language models through task arithmetic☆25Updated 5 months ago
- ☆31Updated 3 months ago
- Weak-to-Strong Jailbreaking on Large Language Models☆62Updated 6 months ago
- The dataset and code for the ICLR 2024 paper "Can LLM-Generated Misinformation Be Detected?"☆45Updated last month
- Code for "Universal Adversarial Triggers Are Not Universal."☆15Updated 4 months ago
- A resource repository for representation engineering in large language models☆36Updated last week
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents☆57Updated last month
- [EMNLP 2023] Poisoning Retrieval Corpora by Injecting Adversarial Passages https://arxiv.org/abs/2310.19156☆21Updated 9 months ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆67Updated last week