Optimizing Adaptive Attacks against Content Watermarks for Language Models.
CoRR, 2024
PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting.
Proceedings of the 33rd USENIX Security Symposium, 2024
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions.
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the 33rd USENIX Security Symposium, 2024
Universal Backdoor Attacks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Leveraging Optimization for Adaptive Attacks on Image Watermarks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Privacy-Preserving Machine Learning [Cryptography].
IEEE Secur. Priv., 2023
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks against Deep Image Classification.
CoRR, 2023
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators.
Proceedings of the 32nd USENIX Security Symposium, 2023
Analyzing Leakage of Personally Identifiable Information in Language Models.
Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023
SoK: How Robust is Image Classification Deep Neural Network Watermarking?
Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022
SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version).
CoRR, 2021
On the Robustness of Backdoor-based Watermarking in Deep Neural Networks.
Proceedings of the IH&MMSec '21: ACM Workshop on Information Hiding and Multimedia Security, 2021
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples.
Proceedings of the 9th International Conference on Learning Representations, 2021
Differentially Private Two-Party Set Operations.
Proceedings of the IEEE European Symposium on Security and Privacy, 2020
Practical Over-Threshold Multi-Party Private Set Intersection.
Proceedings of the ACSAC '20: Annual Computer Security Applications Conference, 2020
On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks.
CoRR, 2019