On the robustness of vision transformers to adversarial examples

K Mahmood, R Mahmood… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Recent advances in attention-based networks have shown that Vision Transformers can
achieve state-of-the-art or near state-of-the-art results on many image classification tasks …

Back in black: A comparative evaluation of recent state-of-the-art black-box attacks

K Mahmood, R Mahmood, E Rathbun… - IEEE Access, 2021 - ieeexplore.ieee.org
The field of adversarial machine learning has experienced a near exponential growth in the
amount of papers being produced since 2018. This massive information output has yet to be …

How to Defend and Secure Deep Learning Models Against Adversarial Attacks in Computer Vision: A Systematic Review

L Dhamija, U Bansal - New Generation Computing, 2024 - Springer
Deep learning plays a significant role in develo** a robust and constructive framework for
tackling complex learning tasks. Consequently, it is widely utilized in many security-critical …

Adversarial adaptive neighborhood with feature importance-aware convex interpolation

Q Li, Y Qi, Q Hu, S Qi, Y Lin… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Adversarial Examples threaten to fool deep learning models to output erroneous predictions
with high confidence. Optimization-based methods for constructing such samples have been …

Beware the black-box: On the robustness of recent defenses to adversarial examples

K Mahmood, D Gurevin, M van Dijk, PH Nguyen - Entropy, 2021 - mdpi.com
Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR.
These defenses are mainly focused on mitigating white-box attacks. They do not properly …

Practical black-box adversarial attack on open-set recognition: Towards robust autonomous driving

Y Wang, K Zhang, K Lu, Y **ong, M Wen - Peer-to-Peer Networking and …, 2023 - Springer
As an important method of image classification, Open-Set Recognition (OSR) has been
gradually deployed in autonomous driving systems (ADSs) for detecting the surrounding …

[BOOK][B] Generative Models as a Robust Alternative for Image Classification: Progress and Challenge

A Ju - 2021 - search.proquest.com
The tremendous success of neural networks is clouded by the existence of adversarial
examples: maliciously engineered inputs can cause neural networks to perform abnormally …

Rοbustness οf neural netwοrk image classifiers tο meaningful adversarial examples

L Anquetil - 2023 - theses.hal.science
Machine learning is revolutionizing the world in many ways, enabling the creation of artificial
systems capable of performing complex tasks. In medicine, machine learning systems are …

[BOOK][B] Designing Deep Networks for Adversarial Robustness and Security

KR Mahmood - 2022 - search.proquest.com
The advent of adversarial machine learning fundamentally challenges the widespread
adoption of Convolutional Neural Networks (CNNs), Vision Transformers and other deep …