 MaskPure: Improving Defense Against Text Adversaries with Stochastic
PurificationInternational Conference on Applications of Natural Language to Data Bases (NLDB), 2024 |
 MalProtect: Stateful Defense Against Adversarial Query Attacks in
ML-based Malware DetectionIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023 |
 On the Perils of Cascading Robust ClassifiersInternational Conference on Learning Representations (ICLR), 2022 |
 Searching for an Effective Defender: Benchmarking Defense against
Adversarial Word SubstitutionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
![Certified Robustness to Text Adversarial Attacks by Randomized [MASK]](https://cdn.parameterlab.de/resized-images/aHR0cHM6Ly9jZG4ucGFyYW1ldGVybGFiLmRlL3BhcGVycy8yMTA1LjAzNzQzL3BhZ2VzL3BhZ2UtMS1xODBkMzAwLmpwZw?w=256&q=75&f=webp) Certified Robustness to Text Adversarial Attacks by Randomized [MASK]International Conference on Computational Logic (ICCL), 2021 |
