RockyLzy / TextDefender
codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"
☆31Updated last year
Alternatives and similar repositories for TextDefender:
Users that are interested in TextDefender are comparing it to the libraries listed below
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆17Updated last year
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆29Updated 2 years ago
- For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]☆15Updated 4 months ago
- ☆24Updated 3 years ago
- SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)☆29Updated 4 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆32Updated 3 years ago
- Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks☆24Updated 4 years ago
- Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021☆43Updated 3 years ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆27Updated last year
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆69Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆24Updated 3 years ago
- Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples (EACL 2021)☆8Updated 3 years ago
- Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"☆103Updated 2 years ago
- Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"☆41Updated 2 years ago
- Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversaria…☆42Updated 2 years ago
- Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples☆35Updated 5 years ago
- ☆14Updated 2 years ago
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆38Updated 3 years ago
- ☆41Updated 3 weeks ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆36Updated 7 months ago
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆48Updated 10 months ago
- Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)☆38Updated 5 years ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆46Updated 3 years ago
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆20Updated last year
- Natural Universal Trigger Search (NUTS)☆21Updated 3 years ago
- ☆37Updated last year
- ☆9Updated 3 years ago
- ☆24Updated 3 years ago
- ☆21Updated last year
- Official Code for ACL 2023 paper: "Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confid…☆22Updated last year