lancopku / Embedding-Poisoning
Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-HLT 2021)
☆40Updated 3 years ago
Alternatives and similar repositories for Embedding-Poisoning:
Users that are interested in Embedding-Poisoning are comparing it to the libraries listed below
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 9 months 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 "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆24Updated 3 years ago
- ☆25Updated 3 years ago
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆24Updated 3 years ago
- Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"☆42Updated 2 years ago
- ☆17Updated 3 years ago
- ☆42Updated 2 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- ☆18Updated 3 years ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆107Updated 2 years ago
- Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"☆16Updated 3 years ago
- ☆24Updated last year
- A curated list of trustworthy Generative AI papers. Daily updating...☆71Updated 7 months ago
- Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples☆35Updated 6 years ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆52Updated last year
- ☆21Updated last year
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆28Updated 5 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆70Updated 6 months ago
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Updated 4 years ago
- Fingerprint large language models☆34Updated 9 months ago
- ☆54Updated 10 months ago
- ☆42Updated last year
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆83Updated 3 months ago
- Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"☆18Updated 9 months ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 6 months ago
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆26Updated 3 years ago