facebookresearch / three_bricks
Official Implementation of the paper "Three Bricks to Consolidate Watermarks for LLMs"
☆46Updated last year
Alternatives and similar repositories for three_bricks:
Users that are interested in three_bricks are comparing it to the libraries listed below
- Code for watermarking language models☆78Updated 7 months ago
- ☆24Updated 2 months ago
- [ICLR 2024] Provable Robust Watermarking for AI-Generated Text☆33Updated last year
- ☆33Updated 4 months ago
- ☆18Updated last year
- ☆54Updated 2 years ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆76Updated 3 weeks ago
- ☆36Updated 8 months ago
- [ICLR 2025] Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs☆17Updated last month
- Official repository of the paper: Who Wrote this Code? Watermarking for Code Generation (ACL 2024)☆33Updated 10 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆98Updated this week
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆28Updated 5 months ago
- ☆42Updated 2 months ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆86Updated 11 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆58Updated 6 months ago
- [ICML 2024] Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models☆22Updated 7 months ago
- Implementation of paper 'Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference' [NeurIPS'24…☆16Updated 10 months ago
- Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)☆60Updated 3 months ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆80Updated 11 months ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆107Updated 2 years ago
- [ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)☆77Updated 6 months ago
- ☆57Updated 9 months ago
- [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs☆37Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆95Updated 2 months ago
- Code for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder" in NMI.☆47Updated last year
- [ICML2024] Adaptive Text Watermark for Large Language Models☆16Updated 4 months ago
- Official repository for "PostMark: A Robust Blackbox Watermark for Large Language Models"☆24Updated 7 months ago
- ☆35Updated 6 months ago
- Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024☆33Updated 11 months ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆51Updated last month