Web: http://arxiv.org/abs/2208.03309

Sept. 19, 2022, 1:14 a.m. | Wenxiao Wang, Alexander Levine, Soheil Feizi

cs.CV updates on arXiv.org arxiv.org

Data poisoning considers an adversary that distorts the training set of
machine learning algorithms for malicious purposes. In this work, we bring to
light one conjecture regarding the fundamentals of data poisoning, which we
call the Lethal Dose Conjecture. The conjecture states: If $n$ clean training
samples are needed for accurate predictions, then in a size-$N$ training set,
only $\Theta(N/n)$ poisoned samples can be tolerated while ensuring accuracy.
Theoretically, we verify this conjecture in multiple cases. We also offer a …

arxiv data

More from arxiv.org / cs.CV updates on arXiv.org

Research Scientists

@ ODU Research Foundation | Norfolk, Virginia

Embedded Systems Engineer (Robotics)

@ Neo Cybernetica | Bedford, New Hampshire

2023 Luis J. Alvarez and Admiral Grace M. Hopper Postdoc Fellowship in Computing Sciences

@ Lawrence Berkeley National Lab | San Francisco, CA

Senior Manager Data Scientist

@ NAV | Remote, US

Senior AI Research Scientist

@ Earth Species Project | Remote anywhere

Research Fellow- Center for Security and Emerging Technology (Multiple Opportunities)

@ University of California Davis | Washington, DC

Staff Fellow - Data Scientist

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Staff Fellow - Senior Data Engineer

@ U.S. FDA/Center for Devices and Radiological Health | Silver Spring, Maryland

Tech Business Data Analyst

@ Fivesky | Alpharetta, GA

Senior Applied Scientist

@ Amazon.com | London, England, GBR

AI Researcher (Junior/Mid-level)

@ Charles River Analytics Inc. | Cambridge, MA

Data Engineer - Machine Learning & AI

@ Calabrio | Minneapolis, Minnesota, United States