Clustering and ensemble based approach for securing electricity theft detectors against evasion attacks

I Elgarhy, MM Badr, MMEA Mahmoud, MM Fouda… - IEEE …, 2023 - ieeexplore.ieee.org
In smart power grids, electricity theft causes huge economic losses to electrical utility
companies. Machine learning (ML), especially deep neural network (DNN) models hold …

Zero-query adversarial attack on black-box automatic speech recognition systems

Z Fang, T Wang, L Zhao, S Zhang, B Li, Y Ge… - Proceedings of the …, 2024 - dl.acm.org
In recent years, extensive research has been conducted on the vulnerability of ASR systems,
revealing that black-box adversarial example attacks pose significant threats to real-world …

Securing smart grid false data detectors against white-box evasion attacks without sacrificing accuracy

I Elgarhy, MM Badr, M Mahmoud… - IEEE Internet of …, 2024 - ieeexplore.ieee.org
In the realm of smart grids, smart meters can be hacked to report false data to lower the
consumers' electricity bills. While machine learning (ML) techniques have shown promise in …

Ensemble learning methods of adversarial attacks and defenses in computer vision: Recent progress

Z Lu, H Hu, S Huo, S Li - 2021 International Conference on …, 2022 - ieeexplore.ieee.org
Artificial intelligence (AI) has developed rapidly in recent decades and is widely used in
many fields, such as natural language processing, voice recognition, and especially …

On Inherent Adversarial Robustness of Active Vision Systems

A Mukherjee, T Ibrayev, K Roy - Transactions on Machine Learning …, 2024 - openreview.net
Deep Neural Networks (DNNs) are susceptible to adversarial inputs, such as imperceptible
noise and naturally occurring challenging samples. This vulnerability likely arises from their …

HARDWARE-AWARE EFFICIENT AND ROBUST DEEP LEARNING

S Krithivasan - 2022 - hammer.purdue.edu
Deep Neural Networks (DNNs) have greatly advanced several domains of machine learning
including image, speech and natural language processing, leading to their usage in several …