nuaa-nlp / TrustworthyAIPapers
List of Papers on Attack and Defense (AD) in AI Models
☆25Updated 2 years ago
Related projects: ⓘ
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆23Updated 3 years ago
- ☆22Updated 3 years ago
- Natural Universal Trigger Search (NUTS)☆21Updated 3 years ago
- Zero-shot Learning by Generating Task-specific Adapters☆14Updated 3 years ago
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆28Updated 2 years ago
- Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022☆26Updated 2 years ago
- ☆25Updated 3 years ago
- [ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Y…☆82Updated 10 months ago
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆66Updated last year
- ☆20Updated 3 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆38Updated last year
- Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…☆34Updated 3 years ago
- MATCH-TUNING☆15Updated 2 years ago
- [EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Q…☆26Updated 2 years ago
- Code for CascadeBERT, Findings of EMNLP 2021☆11Updated 2 years ago
- code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification☆26Updated 2 years ago
- Code for the paper "Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers"☆17Updated 3 years ago
- Code for our paper: "GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models"☆50Updated last year
- The source code of our ACL paper "A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance an…☆14Updated last year
- Code for ACL 2023 paper "A Close Look into the Calibration of Pre-trained Language Models"☆12Updated last year
- Code for EMNLP'21 paper "Types of Out-of-Distribution Texts and How to Detect Them"☆25Updated 2 years ago
- ☆13Updated 3 years ago
- ☆25Updated 2 years ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆36Updated 3 months ago
- ☆18Updated last year
- Code for ACL 2021 paper "Unsupervised Out-of-Domain Detection via Pre-trained Transformers"☆30Updated 3 years ago
- Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples☆32Updated 5 years ago
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆15Updated last year
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆20Updated 2 years ago
- Code for our AAAI2021 paper: Token-Aware Virtual Adversarial Training For Language Understanding.☆26Updated 3 years ago