lancopku / SOSLinks
Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
☆24Updated 3 years ago
Alternatives and similar repositories for SOS
Users that are interested in SOS are comparing it to the libraries listed below
Sorting:
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆24Updated 3 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆42Updated 2 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆39Updated last year
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆16Updated 4 years ago
- ☆18Updated 4 years ago
- Fingerprint large language models☆41Updated last year
- Hidden backdoor attack on NLP systems☆47Updated 3 years ago
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆41Updated 4 years ago
- TrojanLM: Trojaning Language Models for Fun and Profit☆16Updated 4 years ago
- ☆25Updated 4 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆43Updated 2 years ago
- Source code of paper "An Unforgeable Publicly Verifiable Watermark for Large Language Models" accepted by ICLR 2024☆35Updated last year
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆30Updated 3 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆34Updated 3 years ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆34Updated 9 months ago
- Robust natural language watermarking using invariant features☆26Updated last year
- ☆25Updated 2 years ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆34Updated last year
- ☆18Updated 3 years ago
- A curated list of trustworthy Generative AI papers. Daily updating...☆73Updated 11 months ago
- An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)☆189Updated 2 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆108Updated 2 years ago
- ☆20Updated last year
- Watermarking Text Generated by Black-Box Language Models☆39Updated last year
- ☆18Updated 3 years ago
- ☆31Updated 3 years ago
- This is the code repository of our submission: Understanding the Dark Side of LLMs’ Intrinsic Self-Correction.☆61Updated 8 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆57Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆34Updated 7 months ago
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆15Updated 10 months ago