McGill-NLP / AdversarialTriggersLinks
Code for "Universal Adversarial Triggers Are Not Universal."
☆17Updated last year
Alternatives and similar repositories for AdversarialTriggers
Users that are interested in AdversarialTriggers are comparing it to the libraries listed below
Sorting:
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- ☆55Updated 2 years ago
- ☆41Updated 10 months ago
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆96Updated last year
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆64Updated 6 months ago
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 2 months ago
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆18Updated last year
- ☆44Updated 2 years ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆57Updated last year
- ☆17Updated last month
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆74Updated 5 months ago
- The official repository of the paper "On the Exploitability of Instruction Tuning".☆64Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆85Updated last year
- ☆44Updated 6 months ago
- [ICML 2025] Weak-to-Strong Jailbreaking on Large Language Models☆84Updated 3 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆59Updated last month
- ☆35Updated 7 months ago
- Official Repository for Dataset Inference for LLMs☆36Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆106Updated 5 months ago
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆18Updated last year
- ☆29Updated last year
- ☆47Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆36Updated 5 months ago
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆21Updated 2 months ago
- ☆43Updated last year
- Official implementation of ICLR'24 paper, "Curiosity-driven Red Teaming for Large Language Models" (https://openreview.net/pdf?id=4KqkizX…☆78Updated last year
- ☆31Updated 2 years ago
- ☆21Updated 6 months ago
- ☆31Updated last year
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90Updated last year