leix28 / prompt-universal-vulnerabilityLinks
Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
☆29Updated 2 years ago
Alternatives and similar repositories for prompt-universal-vulnerability
Users that are interested in prompt-universal-vulnerability are comparing it to the libraries listed below
Sorting:
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 10 months ago
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆40Updated 3 years ago
- ☆44Updated 3 months ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆33Updated 3 years ago
- ☆25Updated 3 years ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- ☆56Updated last year
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆18Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆24Updated 3 years ago
- Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confid…☆23Updated 2 years ago
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆21Updated 2 years ago
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆24Updated 3 years ago
- ☆41Updated 8 months ago
- Code for "Universal Adversarial Triggers Are Not Universal."☆17Updated last year
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 2 years ago
- Official Repository for Dataset Inference for LLMs☆34Updated 10 months ago
- ☆18Updated 3 years ago
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆26Updated 3 years ago
- ☆24Updated last year
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆33Updated last year
- Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"☆18Updated last year
- ☆21Updated 2 months ago
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Updated 10 months ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆35Updated 11 months ago
- Natural Universal Trigger Search (NUTS)☆21Updated 4 years ago
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆51Updated 7 months ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆32Updated 6 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆93Updated last year
- ☆21Updated last year