THU-BPM / unforgeable_watermark

Related projects: ⓘ

• THU-BPM / Robust_Watermark
  Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.
  ☆25Updated 3 months ago
• lancopku / codable-watermarking-for-llm
  Repository for Towards Codable Watermarking for Large Language Models
  ☆26Updated last year
• bangawayoo / nlp-watermarking
  Robust natural language watermarking using invariant features
  ☆25Updated 11 months ago
• chenchenygu / watermark-learnability
  ☆18Updated 3 months ago
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆37Updated 2 years ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆32Updated 2 months ago
• hongcheki / sweet-watermark
  Official repository of the paper: Who Wrote this Code? Watermarking for Code Generation (ACL 2024)
  ☆23Updated 3 months ago
• lancopku / SOS
  Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
  ☆21Updated 2 years ago
• THU-KEG / WaterBench
  [ACL2024-Main] Data and Code for WaterBench: Towards Holistic Evaluation of LLM Watermarks
  ☆17Updated 10 months ago
• thunlp / BkdAtk-LWS
  Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"
  ☆15Updated 3 years ago
• ZhentingWang / DIAGNOSIS
  ☆14Updated 4 months ago
• XuandongZhao / Ginsew
  [ICML 2023] Protecting Language Generation Models via Invisible Watermarking
  ☆13Updated last year
• Kiode / Text_Watermark
  Watermarking Text Generated by Black-Box Language Models
  ☆28Updated 9 months ago
• yjw1029 / EmbMarker
  Code and data for our paper "Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark"…
  ☆47Updated last year
• Lyz1213 / BadEdit
  ☆12Updated 5 months ago
• jthickstun / watermark
  Code for watermarking language models
  ☆69Updated last week
• grasses / PoisonPrompt
  Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107
  ☆9Updated last month
• isXinLiu / MM-SafetyBench
  Accepted by ECCV 2024
  ☆59Updated 2 months ago
• AISG-Technology-Team / GCSS-Track-1A-Submission-Guide
  Submission Guide + Discussion Board for AI Singapore Global Challenge for Safe and Secure LLMs (Track 1A).
  ☆16Updated 2 months ago
• zhaisf / BadT2I
  [MM'23 Oral] "Text-to-image diffusion models can be easily backdoored through multimodal data poisoning"
  ☆19Updated last week
• wagner-group / MarkMyWords
  ☆23Updated 3 months ago
• XuandongZhao / DRW
  [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP
  ☆12Updated last year
• byerose / Awesome-Foundation-Model-Security
  A curated list of trustworthy Generative AI papers. Daily updating...
  ☆67Updated 2 weeks ago
• meng-wenlong / LMSanitator
  ☆15Updated last year
• SCLBD / DBD
  ☆27Updated 2 years ago
• thu-coai / JailbreakDefense_GoalPriority
  [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
  ☆11Updated 2 months ago
• Eyr3 / TextCRS
  Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks (IEEE S&P 2024)
  ☆29Updated 6 months ago
• thunlp / NeuBA
  ☆22Updated 3 years ago
• jiaxiaojunQAQ / I-GCG
  Improved techniques for optimization-based jailbreaking on large language models
  ☆33Updated 3 months ago
• xiaoniu-578fa6bff964d005 / UnbiasedWatermark
  ☆27Updated last month