Search

Your search keyword '"Weissbart, Leo"' showing total 11 results
Start Over Author "Weissbart, Leo"

Refine your results

11 results on '"Weissbart, Leo"'

1. CNN architecture extraction on edge GPU

Author

Horvath, Peter, Chmielewski, Lukasz, Weissbart, Leo, Batina, Lejla, and Yarom, Yuval

Subjects
Computer Science - Cryptography and Security, Computer Science - Machine Learning
Abstract

Neural networks have become popular due to their versatility and state-of-the-art results in many applications, such as image classification, natural language processing, speech recognition, forecasting, etc. These applications are also used in resource-constrained environments such as embedded devices. In this work, the susceptibility of neural network implementations to reverse engineering is explored on the NVIDIA Jetson Nano microcomputer via side-channel analysis. To this end, an architecture extraction attack is presented. In the attack, 15 popular convolutional neural network architectures (EfficientNets, MobileNets, NasNet, etc.) are implemented on the GPU of Jetson Nano and the electromagnetic radiation of the GPU is analyzed during the inference operation of the neural networks. The results of the analysis show that neural network architectures are easily distinguishable using deep learning-based side-channel analysis., Comment: Will appear at the AIHWS 2024 workshop at ACNS 2024

Published
2024

2. BarraCUDA: Edge GPUs do Leak DNN Weights

Author

Horvath, Peter, Chmielewski, Lukasz, Weissbart, Leo, Batina, Lejla, and Yarom, Yuval

Subjects
Computer Science - Cryptography and Security
Abstract

Over the last decade, applications of neural networks (NNs) have spread to various aspects of our lives. A large number of companies base their businesses on building products that use neural networks for tasks such as face recognition, machine translation, and self-driving cars. Much of the intellectual property underpinning these products is encoded in the exact parameters of the neural networks. Consequently, protecting these is of utmost priority to businesses. At the same time, many of these products need to operate under a strong threat model, in which the adversary has unfettered physical control of the product. In this work, we present BarraCUDA, a novel attack on general purpose Graphic Processing Units (GPUs) that can extract parameters of neural networks running on the popular Nvidia Jetson Nano device. BarraCUDA uses correlation electromagnetic analysis to recover parameters of real-world convolutional neural networks., Comment: To appear in USENIX Security 2025

Published
2023

3. Everything All at Once: Deep Learning Side-Channel Analysis Optimization Framework

Author

Serafini, Gabriele, Weissbart, Léo, Batina, Lejla, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, van Leeuwen, Jan, Series Editor, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Kobsa, Alfred, Series Editor, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Nierstrasz, Oscar, Series Editor, Pandu Rangan, C., Editorial Board Member, Sudan, Madhu, Series Editor, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Vardi, Moshe Y, Series Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, and Andreoni, Martin, editor

Published
2024
Full Text
View/download PDF

4. One for All, All for Ascon: Ensemble-Based Deep Learning Side-Channel Analysis

Author

Rezaeezade, Azade, Basurto-Becerra, Abraham, Weissbart, Léo, Perin, Guilherme, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, van Leeuwen, Jan, Series Editor, Hutchison, David, Editorial Board Member, Kanade, Takeo, Editorial Board Member, Kittler, Josef, Editorial Board Member, Kleinberg, Jon M., Editorial Board Member, Kobsa, Alfred, Series Editor, Mattern, Friedemann, Editorial Board Member, Mitchell, John C., Editorial Board Member, Naor, Moni, Editorial Board Member, Nierstrasz, Oscar, Series Editor, Pandu Rangan, C., Editorial Board Member, Sudan, Madhu, Series Editor, Terzopoulos, Demetri, Editorial Board Member, Tygar, Doug, Editorial Board Member, Weikum, Gerhard, Series Editor, Vardi, Moshe Y, Series Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, and Andreoni, Martin, editor

Published
2024
Full Text
View/download PDF

5. Screen Gleaning: A Screen Reading TEMPEST Attack on Mobile Devices Exploiting an Electromagnetic Side Channel

Author

Liu, Zhuoran, Samwel, Niels, Weissbart, Léo, Zhao, Zhengyu, Lauret, Dirk, Batina, Lejla, and Larson, Martha

Subjects
Computer Science - Cryptography and Security
Abstract

We introduce screen gleaning, a TEMPEST attack in which the screen of a mobile device is read without a visual line of sight, revealing sensitive information displayed on the phone screen. The screen gleaning attack uses an antenna and a software-defined radio (SDR) to pick up the electromagnetic signal that the device sends to the screen to display, e.g., a message with a security code. This special equipment makes it possible to recreate the signal as a gray-scale image, which we refer to as an emage. Here, we show that it can be used to read a security code. The screen gleaning attack is challenging because it is often impossible for a human viewer to interpret the emage directly. We show that this challenge can be addressed with machine learning, specifically, a deep learning classifier. Screen gleaning will become increasingly serious as SDRs and deep learning continue to rapidly advance. In this paper, we demonstrate the security code attack and we propose a testbed that provides a standard setup in which screen gleaning could be tested with different attacker models. Finally, we analyze the dimensions of screen gleaning attacker models and discuss possible countermeasures with the potential to address them., Comment: To appear at NDSS 2021

Published
2020

6. On Reverse Engineering Neural Network Implementation on GPU

Author

Chmielewski, Łukasz, Weissbart, Léo, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Zhou, Jianying, editor, Ahmed, Chuadhry Mujeeb, editor, Batina, Lejla, editor, Chattopadhyay, Sudipta, editor, Gadyatskaya, Olga, editor, Jin, Chenglu, editor, Lin, Jingqiang, editor, Losiouk, Eleonora, editor, Luo, Bo, editor, Majumdar, Suryadipta, editor, Maniatakos, Mihalis, editor, Mashima, Daisuke, editor, Meng, Weizhi, editor, Picek, Stjepan, editor, Shimaoka, Masaki, editor, Su, Chunhua, editor, and Wang, Cong, editor

Published
2021
Full Text
View/download PDF

7. Performance Analysis of Multilayer Perceptron in Profiling Side-Channel Analysis

Author

Weissbart, Léo, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Zhou, Jianying, editor, Conti, Mauro, editor, Ahmed, Chuadhry Mujeeb, editor, Au, Man Ho, editor, Batina, Lejla, editor, Li, Zhou, editor, Lin, Jingqiang, editor, Losiouk, Eleonora, editor, Luo, Bo, editor, Majumdar, Suryadipta, editor, Meng, Weizhi, editor, Ochoa, Martín, editor, Picek, Stjepan, editor, Portokalidis, Georgios, editor, Wang, Cong, editor, and Zhang, Kehuan, editor

Published
2020
Full Text
View/download PDF

8. One Trace Is All It Takes: Machine Learning-Based Side-Channel Attack on EdDSA

Author

Weissbart, Léo, Picek, Stjepan, Batina, Lejla, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Bhasin, Shivam, editor, Mendelson, Avi, editor, and Nandi, Mridul, editor

Published
2019
Full Text
View/download PDF

9. BarraCUDA: GPUs do Leak DNN Weights

Author

Horvath, Peter, Chmielewski, Lukasz, Weissbart, Leo, Batina, Lejla, Yarom, Yuval, Horvath, Peter, Chmielewski, Lukasz, Weissbart, Leo, Batina, Lejla, and Yarom, Yuval

Abstract

Over the last decade, applications of neural networks (NNs) have spread to various aspects of our lives. A large number of companies base their businesses on building products that use neural networks for tasks such as face recognition, machine translation, and self-driving cars. Much of the intellectual property underpinning these products is encoded in the exact parameters of the neural networks. Consequently, protecting these is of utmost priority to businesses. At the same time, many of these products need to operate under a strong threat model, in which the adversary has unfettered physical control of the product. In this work, we present BarraCUDA, a novel attack on general purpose Graphic Processing Units (GPUs) that can extract parameters of neural networks running on the popular Nvidia Jetson Nano device. BarraCUDA uses correlation electromagnetic analysis to recover parameters of real-world convolutional neural networks.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results