THU-BPM / unforgeable_watermark
Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024
☆32Updated 9 months ago
Alternatives and similar repositories for unforgeable_watermark:
Users that are interested in unforgeable_watermark are comparing it to the libraries listed below
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆27Updated 4 months ago
- Official repository of the paper: Who Wrote this Code? Watermarking for Code Generation (ACL 2024)☆33Updated 9 months ago
- Repository for Towards Codable Watermarking for Large Language Models☆35Updated last year
- ☆36Updated 7 months ago
- Robust natural language watermarking using invariant features☆26Updated last year
- ☆18Updated 11 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 8 months ago
- [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images☆30Updated last year
- Code for watermarking language models☆75Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆42Updated 2 months ago
- Watermarking Text Generated by Black-Box Language Models☆33Updated last year
- Submission Guide + Discussion Board for AI Singapore Global Challenge for Safe and Secure LLMs (Track 1A).☆16Updated 8 months ago
- [ECCV 2024] Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"☆77Updated last year
- ☆24Updated last month
- ☆19Updated 10 months ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆13Updated 5 months ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆19Updated 8 months ago
- ☆32Updated 3 months ago
- AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models☆50Updated 11 months ago
- [ECCV'24 Oral] The official GitHub page for ''Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking …☆17Updated 4 months ago
- [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks☆23Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 10 months ago
- ☆9Updated 3 years ago
- A package that achieves 95%+ transfer attack success rate against GPT-4☆16Updated 4 months ago
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆55Updated 2 months ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆17Updated 7 months ago
- A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)☆134Updated last week