leix28 / prompt-universal-vulnerabilityLinks
Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
☆30Updated 3 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 "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆42Updated 4 years ago
- ☆56Updated last year
- ☆25Updated 4 years ago
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆21Updated 2 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆34Updated 3 years ago
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆25Updated 3 years ago
- ☆46Updated 7 months ago
- Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆24Updated 3 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆39Updated last year
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆43Updated 3 years ago
- Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"☆20Updated last year
- A lightweight library for large laguage model (LLM) jailbreaking defense.☆57Updated 3 weeks ago
- Code and data for paper "A Semantic Invariant Robust Watermark for Large Language Models" accepted by ICLR 2024.☆34Updated 10 months ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆31Updated last year
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆26Updated 4 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
- [ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning☆98Updated last year
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆109Updated 2 years ago
- Natural Universal Trigger Search (NUTS)☆21Updated 4 years ago
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆18Updated 2 years ago
- ☆43Updated 2 years ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆36Updated last year
- [ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer☆46Updated last year
- Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021☆43Updated 4 years ago
- ☆26Updated last year
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆82Updated last year
- ☆38Updated last year
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆87Updated last year
- ☆21Updated 6 months ago
- Code for paper "Defending aginast LLM Jailbreaking via Backtranslation"☆30Updated last year