190 citations · 451 across the 12 of their papers we have counts for
15 papers
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,…
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…
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…
SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning
Ahmed Salem, Giovanni Cherubin, David Evans +5
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of in…
UnGANable: Defending Against GAN-based Face Manipulation
Zheng Li, Ning Yu, Ahmed Salem +3
Deepfakes pose severe threats of visual misinformation to our society. One representative deepfake application is face manipulation that modifies a victim's facial attributes in an…
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +6
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that su…