Nils Lukas

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 22

Top Topics

Set Intersection

Image Classification

Image Watermarking

Top Venues

USENIX Security Symposium

IEEE Symposium on Security and Privacy

Publications

Benjamin Schneider, Nils Lukas, Florian Kerschbaum
Universal Backdoor Attacks. ICLR (2024)
Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum
Leveraging Optimization for Adaptive Attacks on Image Watermarks. ICLR (2024)
Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani, Thomas Humphries, Bailey Kacsmar, John A. Premkumar, Xinda Li, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting. USENIX Security Symposium (2024)
Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz, Faezeh Ebrahimianghazani, Bailey Kacsmar, Xinda Li, Nils Lukas, Rasoul Akhavan Mahdavi, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions. USENIX Security Symposium (2024)
Nils Lukas, Florian Kerschbaum
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks against Deep Image Classification. CoRR (2023)
Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani, Thomas Humphries, Bailey Kacsmar, John A. Premkumar, Xinda Li, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting. CoRR (2023)
Nils Lukas, Florian Kerschbaum
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators. USENIX Security Symposium (2023)
Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella Béguelin
Analyzing Leakage of Personally Identifiable Information in Language Models. CoRR (2023)
Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz, Faezeh Ebrahimianghazani, Bailey Kacsmar, Xinda Li, Nils Lukas, Rasoul Akhavan Mahdavi, Simon Oya, Ehsan Amjadian, Florian Kerschbaum
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions. CoRR (2023)
Benjamin Schneider, Nils Lukas, Florian Kerschbaum
Universal Backdoor Attacks. CoRR (2023)
Nils Lukas, Florian Kerschbaum
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators. CoRR (2023)
Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum
Leveraging Optimization for Adaptive Attacks on Image Watermarks. CoRR (2023)
Florian Kerschbaum, Nils Lukas
Privacy-Preserving Machine Learning [Cryptography]. IEEE Secur. Priv. 21 (6) (2023)
Nils Lukas, Ahmed Salem, Robert Sim, Shruti Tople, Lukas Wutschitz, Santiago Zanella Béguelin
Analyzing Leakage of Personally Identifiable Information in Language Models. SP (2023)
Nils Lukas, Edward Jiang, Xinda Li, Florian Kerschbaum
SoK: How Robust is Image Classification Deep Neural Network Watermarking? IEEE Symposium on Security and Privacy (2022)
Nils Lukas, Edward Jiang, Xinda Li, Florian Kerschbaum
SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version). CoRR (2021)
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples. ICLR (2021)
Masoumeh Shafieinejad, Nils Lukas, Jiaqi Wang, Xinda Li, Florian Kerschbaum
On the Robustness of Backdoor-based Watermarking in Deep Neural Networks. IH&MMSec (2021)
Bailey Kacsmar, Basit Khurram, Nils Lukas, Alexander Norton, Masoumeh Shafieinejad, Zhiwei Shang, Yaser Baseri, Maryam Sepehri, Simon Oya, Florian Kerschbaum
Differentially Private Two-Party Set Operations. EuroS&P (2020)
Rasoul Akhavan Mahdavi, Thomas Humphries, Bailey Kacsmar, Simeon Krastnikov, Nils Lukas, John A. Premkumar, Masoumeh Shafieinejad, Simon Oya, Florian Kerschbaum, Erik-Oliver Blass
Practical Over-Threshold Multi-Party Private Set Intersection. ACSAC (2020)
Masoumeh Shafieinejad, Jiaqi Wang, Nils Lukas, Florian Kerschbaum
On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks. CoRR (2019)
Nils Lukas, Yuxuan Zhang, Florian Kerschbaum
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples. CoRR (2019)