Towards Practical Robustness Evaluation and Robustness Enhancing
Yaxin Li · Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining · 2022
Deep neural networks (DNNs) have been widely applied on various machine learning tasks and have achieved significant performance across multiple domains. However, it well known that DNNs suffer from severe adversarial vulnerability. Thus it raises great concernswhen DNNs are adopted to safety-critical tasks. These concerns boost the area of adversarial machine learning, which mainly fo-cus on evaluating model robustness through adversarial attacks and gain reliable model performance through adversarial defenses.Among this board topic, my research work focus on a practical perspective. Specifically, there are three subtopics: (1) Enhancing robustness performance for adversarial learning from feature perspective. (2) Standardized and Reliable evaluation for black box attacks under different settings. (3) Building user-friendly adversarial learning tools to help evaluate model robustness. In this research statement, we will mainly focus on these three topics and we will take this opportunity to share our contribution to the relate problems.