xinleihe / toxic-prompt
☆19Updated last year
Related projects ⓘ
Alternatives and complementary repositories for toxic-prompt
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆27Updated 2 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 4 months ago
- Code&Data for the paper "Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents" [NeurIPS 2024]☆45Updated last month
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆21Updated 2 years ago
- ☆38Updated last year
- [USENIX'24] Prompt Stealing Attacks Against Text-to-Image Generation Models☆25Updated last month
- ☆20Updated last year
- Code repo of our paper Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (https://arxiv.org/abs/2406.10794…☆12Updated 3 months ago
- ☆51Updated 5 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆26Updated last year
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆37Updated 3 years ago
- ☆20Updated 9 months ago
- ☆31Updated last year
- ☆18Updated 3 weeks ago
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆22Updated 3 years ago
- ☆18Updated 6 months ago
- Code for Voice Jailbreak Attacks Against GPT-4o.☆27Updated 5 months ago
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Updated 4 years ago
- ☆23Updated 3 years ago
- ☆40Updated last year
- ☆9Updated 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"☆41Updated 2 years ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆39Updated last month
- ☆6Updated 2 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆29Updated 3 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆99Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆41Updated 7 months ago
- Official Repository for Dataset Inference for LLMs☆23Updated 3 months ago
- ☆46Updated 5 months ago
- ☆13Updated 8 months ago