基本信息
浏览量:78
职业迁徙
个人简介
I am a PhD student in the Computer Science department at the University of Maryland, working with Prof. Soheil Feizi and Prof. Tom Goldstein. My research centers around designing machine learning algorithms with mathematical guarantees on their robustness against adversarial attacks. Such attacks can significantly deteriorate the performance of almost any machine learning model just by adding a small amount of noise to the inputs. My recent projects have been focused on developing certified defenses for a wide variety of learning problems ranging from those with structured outputs such as semantic segmentation, image reconstruction, object detection, etc., to the dynamic and adaptive setting of reinforcement learning. The goal of my research is to extend the scope of provable adversarial robustness to complex real-world tasks which cannot be easily modelled as a classification problem.
研究兴趣
论文共 38 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
arXiv (Cornell University) (2023)
引用0浏览0EI引用
0
0
arXiv (Cornell University) (2023)
引用2浏览0引用
2
0
arxiv(2022)
引用0浏览0EI引用
0
0
Indian Journal of Physicsno. 13 (2022): 3817-3830
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn