190 citations · 200 across the 5 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CR2023
Mendata: A Framework to Purify Manipulated Training Data
Zonghao Huang, Neil Gong, Michael K. Reiter
Untrusted data used to train a model might have been manipulated to endow the learned model with hidden properties that the data contributor might later exploit. Data purification…
cs.CR2023★ 1 cited
The Impact of Exposed Passwords on Honeyword Efficacy
Zonghao Huang, Lujo Bauer, Michael K. Reiter
Honeywords are decoy passwords that can be added to a credential database; if a login attempt uses a honeyword, this indicates that the site's credential database has been leaked.…