I'm a Ph.D. student in the computer science department of the University of Virginia. My research interests include the privacy and security of machine learning. I work under the supervision of Mohammad Mahmoody.
Publications: Google Scholar
Peer-reviewed Conference Publications:
Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
Ji Gao, Sanjam Garg, Mohammad Mahmoody, Prashant Nalini Vasudevan.
Polynomial-time targeted attacks on coin-tossing for any number of corruptions
Omid Etesami, Ji Gao, Saeed Mahloujifar, Mohammad Mahmoody - Theory of Cryptography Conference 2021 (TCC 2021)
Learning and Certification under Instance-targeted Poisoning.
Ji Gao, Amin Karbasi, Mohammad Mahmoody - The 37th Conference on Uncertainty in Artificial Intelligence (UAI' 21).
Unsupervised Graph Alignment with Wasserstein Distance Discriminator.
Ji Gao, Xiao Huang, Jundong Li - 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD' 21).
STLnet: Signal Temporal Logic Enforced Multivariate Recurrent Neural Networks.
Meiyi Ma, Ji Gao, Lu Feng, John Stankovic - 2020 Conference on Neural Information Processing Systems (Neurips' 20)
A Fast and Scalable Joint Estimator for Learning Multiple Related Sparse Gaussian Graphical Models.
Beilun Wang, Ji Gao, Yanjun Qi - Artificial Intelligence and Statistics, 2017 (AISTATS' 17)
Workshops and other manuscripts:
Black-box generation of adversarial text sequences to evade deep learning classifiers.
Ji Gao, Jack Lanchantin, Mary Lou Soffa, Yanjun Qi - 2018 IEEE Security and Privacy Workshops (SPW), 50-56
Deepcloak: Masking deep neural network models for robustness against adversarial samples.
Ji Gao, Beilun Wang, Zeming Lin, Weilin Xu, Yanjun Qi - arXiv:1702.06763
A Theoretical Framework for Robustness of (Deep) Classifiers Under Adversarial Noise.
Beilun Wang, Ji Gao, Yanjun Qi - arXiv:1612.00334, 2016