Neuralsanitizer: Detecting backdoors in neural networks

H Zhu, Y Zhao, S Zhang, K Chen - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been pervasively used in many areas, eg, computer
vision, speech recognition, natural language processing, etc. However, recent works show …

FaultGuard: a generative approach to resilient fault prediction in smart electrical grids

E Efatinasab, F Marchiori, A Brighente… - … on Detection of …, 2024 - Springer
Predicting and classifying faults in electricity networks is crucial for uninterrupted provision
and kee** maintenance costs at a minimum. Thanks to the advancements in the field …

Your battery is a blast! safeguarding against counterfeit batteries with authentication

F Marchiori, M Conti - Proceedings of the 2023 ACM SIGSAC …, 2023 - dl.acm.org
Lithium-ion (Li-ion) batteries are the primary power source in various applications due to
their high energy and power density. Their market was estimated to be up to 48 billion US …

CANEDERLI: On The Impact of Adversarial Training and Transferability on CAN Intrusion Detection Systems

F Marchiori, M Conti - Proceedings of the 2024 ACM Workshop on …, 2024 - dl.acm.org
The growing integration of vehicles with external networks has led to a surge in attacks
targeting their Controller Area Network (CAN) internal bus. As a countermeasure, various …

Enhancing cross-domain transferability of black-box adversarial attacks on speaker recognition systems using linearized backpropagation

U Patel, S Bhilare, A Hati - Pattern Analysis and Applications, 2024 - Springer
Speaker recognition system (SRS) serves as the gatekeeper for secure access, using the
unique vocal characteristics of individuals for identification and verification. SRS can be …

Addressing Key Challenges of Adversarial Attacks and Defenses in the Tabular Domain: A Methodological Framework for Coherence and Consistency

Y Itzhakev, A Giloni, Y Elovici, A Shabtai - arxiv preprint arxiv:2412.07326, 2024 - arxiv.org
Machine learning models trained on tabular data are vulnerable to adversarial attacks, even
in realistic scenarios where attackers have access only to the model's outputs. Researchers …

Towards Robust Stability Prediction in Smart Grids: GAN-based Approach under Data Constraints and Adversarial Challenges

E Efatinasab, A Brighente, D Donadel, M Conti… - arxiv preprint arxiv …, 2025 - arxiv.org
Smart grids are critical for addressing the growing energy demand due to global population
growth and urbanization. They enhance efficiency, reliability, and sustainability by …

Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers?

F Marchiori, A Brighente, M Conti - 2024 IEEE European …, 2024 - ieeexplore.ieee.org
Autonomous driving is a research direction that has gained enormous traction in the last few
years thanks to advancements in Artificial Intelligence (AI). Depending on the level of …