all InfoSec news
Poisoning Web-Scale Training Datasets is Practical
May 7, 2024, 4:12 a.m. | Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum Anderson, Andreas Terzis, Kurt Thomas, Florian T
cs.CR updates on arXiv.org arxiv.org
Abstract: Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to a model's performance. Our attacks are immediately practical and could, today, poison 10 popular datasets. Our first attack, split-view poisoning, exploits the mutable nature of internet content to ensure a dataset annotator's initial view of the dataset differs from the view downloaded by subsequent clients. …
arxiv attack attacks crawled cs.cr cs.lg dataset datasets deep learning distributed examples internet malicious performance poisoning poisoning attacks popular scale today training web
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Computer and Forensics Investigator
@ ManTech | 221BQ - Cstmr Site,Springfield,VA
Senior Security Analyst
@ Oracle | United States
Associate Vulnerability Management Specialist
@ Diebold Nixdorf | Hyderabad, Telangana, India