Follow
Nils Lukas
Nils Lukas
MBZUAI
Verified email at mbzuai.ac.ae - Homepage
Title
Cited by
Cited by
Year
Analyzing Leakage of Personally Identifiable Information in Language Models
N Lukas, A Salem, R Sim, S Tople, L Wutschitz, S Zanella-Béguelin
2023 IEEE Symposium on Security and Privacy (S&P), 2023
1792023
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
N Lukas, Y Zhang, F Kerschbaum
The Ninth International Conference on Learning Representations (ICLR 2021), 2021
1642021
On the Robustness of Backdoor-based Watermarking in Deep Neural Networks
M Shafieinejad, N Lukas, J Wang, X Li, F Kerschbaum
Proceedings of the 2021 ACM Workshop on Information Hiding and Multimedia …, 2021
1212021
Sok: How Robust is Image Classification Deep Neural Network Watermarking?
N Lukas, E Jiang, X Li, F Kerschbaum
2022 IEEE Symposium on Security and Privacy (SP), 787-804, 2022
932022
Differentially private two-party set operations
B Kacsmar, B Khurram, N Lukas, A Norton, M Shafieinejad, Z Shang, ...
2020 IEEE European Symposium on Security and Privacy (EuroS&P), 390-404, 2020
242020
Leveraging optimization for adaptive attacks on image watermarks
N Lukas, A Diaa, L Fenaux, F Kerschbaum
The Twelfth International Conference on Learning Representations (ICLR'24), 2024
212024
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators
N Lukas, F Kerschbaum
The 32nd USENIX Security Symposium, 2023
182023
Practical Over-Threshold Multi-Party Private Set Intersection
RA Mahdavi, T Humphries, B Kacsmar, S Krastnikov, N Lukas, ...
Annual Computer Security Applications Conference, 772-783, 2020
162020
SunFlower: A new solar tower simulation method for use in field layout optimization
P Richter, G Heiming, N Lukas, M Frank
AIP Conference Proceedings 2033 (1), 2018
92018
Fast and private inference of deep neural networks by co-designing activation functions
A Diaa, L Fenaux, T Humphries, M Dietz, F Ebrahimianghazani, ...
The 33rd USENIX Security Symposium, 2023
42023
Optimizing adaptive attacks against content watermarks for language models
A Diaa, T Aremu, N Lukas
arXiv preprint arXiv:2410.02440, 2024
12024
Universal Backdoor Attacks
B Schneider, N Lukas, F Kerschbaum
The Twelfth International Conference on Learning Representations (ICLR'24), 2024
12024
PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting
RA Mahdavi, N Lukas, F Ebrahimianghazani, T Humphries, B Kacsmar, ...
USENIX Security, 2024
12024
Privacy-Preserving Machine Learning [Cryptography]
F Kerschbaum, N Lukas
IEEE Security & Privacy 21 (6), 90-94, 2023
12023
Pick your poison: Undetectability versus robustness in data poisoning attacks against deep image classification
N Lukas, F Kerschbaum
arXiv preprint arXiv:2305.09671, 2023
12023
Analyzing Threats of Large-Scale Machine Learning Systems
N Lukas
University of Waterloo, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–16