190 citations · 451 across the 12 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.CL2023
Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
Adel Elmahdy, Ahmed Salem
Natural language processing (NLP) models have become increasingly popular in real-world applications, such as text classification. However, they are vulnerable to privacy attacks,…
cs.CR2023
Two-in-One: A Model Hijacking Attack Against Text Generation Models
Wai Man Si, Michael Backes, Yang Zhang +1
Machine learning has progressed significantly in various applications ranging from face recognition to text generation. However, its success has been accompanied by different attac…
cs.LG2023★ 13 cited
Analyzing Leakage of Personally Identifiable Information in Language Models
Nils Lukas, Ahmed Salem, Robert Sim +3
Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs…