61 citations · 164 across the 9 of their papers we have counts for
Showing 2023 · cs.CRShow all
2 papers · 2 filters
cs.CR2023★ 1 cited
Robust, privacy-preserving, transparent, and auditable on-device blocklisting
Kurt Thomas, Sarah Meiklejohn, Michael A. Specter +4
With the accelerated adoption of end-to-end encryption, there is an opportunity to re-architect security and anti-abuse primitives in a manner that preserves new privacy expectatio…
cs.CR2023★ 15 cited
Poisoning Web-Scale Training Datasets is Practical
Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo +6
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 intentionall…