Biblio

Thudi A, Jia H, Meehan C, Shumailov I, Papernot N.  2024.  Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD. 33rd USENIX Security Symposium (USENIX Security 24). :973--990.

• Google Scholar
• DBLP
• BibTeX

Ahmed S, Wani Y, Shamsabadi AShahin, Yaghini M, Shumailov I, Papernot N, Fawaz K.  2023.  Tubes Among Us: Analog Attack on Automatic Speaker Identification. 32nd USENIX Security Symposium (USENIX Security 23). :265--282.

• Google Scholar
• DBLP
• BibTeX

Thudi A, Jia H, Shumailov I, Papernot N.  2022.  On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning. 31st USENIX Security Symposium (USENIX Security 22). :4007--4022.

• Google Scholar
• DBLP
• BibTeX

Ahmed S, Shumailov I, Papernot N, Fawaz K.  2022.  Towards More Robust Keyword Spotting for Voice Assistants. 31st USENIX Security Symposium (USENIX Security 22). :2655--2672.

• Google Scholar
• DBLP
• BibTeX

Jia H, Choquette-Choo CA, Chandrasekaran V, Papernot N.  2021.  Entangled Watermarks as a Defense against Model Extraction. 30th USENIX Security Symposium (USENIX Security 21). :1937--1954.

• Google Scholar
• DBLP
• BibTeX

Jagielski M, Carlini N, Berthelot D, Kurakin A, Papernot N.  2020.  High Accuracy and High Fidelity Extraction of Neural Networks. 29th USENIX Security Symposium (USENIX Security 20). :1345--1362.

• Google Scholar
• DBLP
• BibTeX

Papernot N.  2019.  Machine Learning at Scale with Differential Privacy in TensorFlow. 2019 {USENIX} Conference on Privacy Engineering Practice and Respect ({PEPR} 19).

• Google Scholar
• DBLP
• BibTeX