no code implementations • 12 Dec 2023 • Ayoub Arous, Andres F Lopez-Lopera, Nael Abu-Ghazaleh, Ihsen Alouani
We model the propagation of noise through the layers, introducing a closed-form stochastic loss function that encapsulates a noise variance parameter.
no code implementations • 30 Nov 2023 • Bilel Tarchoun, Quazi Mishkatul Alam, Nael Abu-Ghazaleh, Ihsen Alouani
Adversarial patches exemplify the tangible manifestation of the threat posed by adversarial attacks on Machine Learning (ML) models in real-world scenarios.
no code implementations • 21 Nov 2023 • Quazi Mishkatul Alam, Bilel Tarchoun, Ihsen Alouani, Nael Abu-Ghazaleh
The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling.
no code implementations • 16 Oct 2023 • Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, Pedram Zaree, Yue Dong, Nael Abu-Ghazaleh
Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows.
no code implementations • 26 Jul 2023 • Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
Specifically, we develop cross-modality attacks on alignment where we pair adversarial images going through the vision encoder with textual prompts to break the alignment of the language model.
no code implementations • 22 Jul 2023 • Quazi Mishkatul Alam, Israat Haque, Nael Abu-Ghazaleh
In this paper, we introduce LtC, a collaborative framework between the video source and the analytics server, that efficiently learns to reduce the video streams within an analytics pipeline.
no code implementations • 17 Jul 2023 • Md Abdullah Al Mamun, Quazi Mishkatul Alam, Erfan Shayegani, Pedram Zaree, Ihsen Alouani, Nael Abu-Ghazaleh
In this paper, we propose a new information theoretic perspective of the problem; we consider the ML model as a storage channel with a capacity that increases with overparameterization.
no code implementations • CVPR 2023 • Bilel Tarchoun, Anouar Ben Khalifa, Mohamed Ali Mahjoub, Nael Abu-Ghazaleh, Ihsen Alouani
Jedi tackles the patch localization problem from an information theory perspective; leverages two new ideas: (1) it improves the identification of potential patch regions using entropy analysis: we show that the entropy of adversarial patches is high, even in naturalistic patches; and (2) it improves the localization of adversarial patches, using an autoencoder that is able to complete patch regions from high entropy kernels.
no code implementations • 5 Jan 2022 • Amira Guesmi, Khaled N. Khasawneh, Nael Abu-Ghazaleh, Ihsen Alouani
Thus, we propose ROOM, a novel Real-time Online-Offline attack construction Model where an offline component serves to warm up the online algorithm, making it possible to generate highly successful attacks under time constraints.
no code implementations • 15 Feb 2021 • Xiangguo Liu, Baiting Luo, Ahmed Abdo, Nael Abu-Ghazaleh, Qi Zhu
While connected vehicle (CV) applications have the potential to revolutionize traditional transportation system, cyber and physical attacks on them could be devastating.
Cryptography and Security
1 code implementation • 13 Jun 2020 • Amira Guesmi, Ihsen Alouani, Khaled Khasawneh, Mouna Baklouti, Tarek Frikha, Mohamed Abid, Nael Abu-Ghazaleh
We show that our approximate computing implementation achieves robustness across a wide range of attack scenarios.
1 code implementation • 20 Jul 2018 • Esmaeil Mohammadian Koruyeh, Khaled Khasawneh, Chengyu Song, Nael Abu-Ghazaleh
In particular, on Core-i7 Skylake and newer processors (but not on Intel's Xeon processor line), a patch called RSB refilling is used to address a vulnerability when the RSB underfills; this defense interferes with SpectreRSB's ability to launch attacks that switch into the kernel.
Cryptography and Security