AI-secure / SemAttack
[NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li
☆19Updated 2 years ago
Related projects: ⓘ
- A Query Efficient Natural Language Attack in a Black Box Setting☆16Updated 2 years ago
- ☆22Updated 3 years ago
- Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks☆23Updated 3 years ago
- 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
- Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)☆20Updated 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
- Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency☆66Updated last year
- For Certified Robustness to Text Adversarial Attacks by Randomized [MASK]☆15Updated 2 years ago
- ☆13Updated 3 years ago
- ACL 2021 - Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble☆15Updated last year
- Natural Universal Trigger Search (NUTS)☆21Updated 3 years ago
- A2T: Towards Improving Adversarial Training of NLP Models (EMNLP 2021 Findings)☆23Updated 3 years ago
- Implementation for Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (EMNLP-Findings 2020)☆15Updated 3 years ago
- codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"☆30Updated 10 months ago
- ☆23Updated 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 last year
- Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"☆28Updated 2 years ago
- Code for ACL2018 HotFlip: White-Box Adversarial Examples for Text Classification, Word-level Adversarial Examples☆32Updated 5 years ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆32Updated 2 months ago
- Official implementation of Privacy Implications of Retrieval-Based Language Models (EMNLP 2023). https://arxiv.org/abs/2305.14888☆36Updated 3 months 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 the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)☆21Updated 2 years ago
- [EMNLP 2022] Distillation-Resistant Watermarking (DRW) for Model Protection in NLP☆12Updated last year
- ☆13Updated 2 years ago
- Contextualized Perturbation for Textual Adversarial Attack, NAACL 2021☆41Updated 3 years ago
- EMNLP BlackBox NLP 2020: Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples☆24Updated 3 years ago
- Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936☆25Updated 3 months ago
- Natural Language Attacks in a Hard Label Black Box Setting.☆40Updated 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
- Mostly recording papers about models' trustworthy applications. Intending to include topics like model evaluation & analysis, security, c…☆18Updated last year