F
Fuching Jack Chi
Researcher at University of California, Berkeley
Publications - 3
Citations - 492
Fuching Jack Chi is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Multi-task learning & Inductive transfer. The author has an hindex of 3, co-authored 3 publications receiving 417 citations. Previous affiliations of Fuching Jack Chi include University of California.
Papers
More filters
Proceedings Article
Exploiting machine learning to subvert your spam filter
Blaine Nelson,Marco Barreno,Fuching Jack Chi,Anthony D. Joseph,Benjamin I. P. Rubinstein,Udam Saini,Charles Sutton,J. D. Tygar,Kai Xia +8 more
TL;DR: This paper shows how an adversary can exploit statistical machine learning, as used in the SpamBayes spam filter, to render it useless--even if the adversary's access is limited to only 1% of the training messages.
Book ChapterDOI
Misleading Learners: Co-opting Your Spam Filter
Blaine Nelson,Marco Barreno,Fuching Jack Chi,Anthony D. Joseph,Benjamin I. P. Rubinstein,Udam Saini,Charles Sutton,J. D. Tygar,Kai Xia +8 more
TL;DR: It is shown how an adversary can exploit statistical machine learning, as used in the SpamBayes spam filter, to make it useless—even if the adversary's access is limited to only 1% of the spam training messages.
Proceedings ArticleDOI
Open problems in the security of learning
Marco Barreno,Peter L. Bartlett,Fuching Jack Chi,Anthony D. Joseph,Blaine Nelson,Benjamin I. P. Rubinstein,Udam Saini,J. D. Tygar +7 more
TL;DR: In this article, the authors present three broad research directions towards the end of developing truly secure learning and suggest lines of investigation into secure techniques for learning in adversarial environments, and suggest that the research directions represent the most important directions to pursue in the quest for secure learning.