LAUSR

Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systems

Sign Up to like & get
recommendations!
0 Published in 2019 at "IEEE Communications Letters"

DOI: 10.1109/lcomm.2019.2901469

Abstract: We show that end-to-end learning of communication systems through deep neural network autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft effective physical black-box adversarial attacks. Due… read more here.

Keywords: end end; adversarial attacks; physical adversarial; communication ... See more keywords

Physical Adversarial Attack on a Robotic Arm

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Robotics and Automation Letters"

DOI: 10.1109/lra.2022.3189783

Abstract: Collaborative Robots (cobots) are regarded as highly safety-critical cyber-physical systems (CPSs) owing to their close physical interactions with humans. In settings such as smart factories, they are frequently augmented with AI. For example, in order… read more here.

Keywords: robotic arm; physical adversarial; adversarial attack; attack robotic ... See more keywords

Robust and Generalized Physical Adversarial Attacks via Meta-GAN

Sign Up to like & get
recommendations!
0 Published in 2024 at "IEEE Transactions on Information Forensics and Security"

DOI: 10.1109/tifs.2023.3288426

Abstract: Deep neural networks are known to be vulnerable to adversarial examples, where adding carefully crafted adversarial perturbations to the inputs can mislead the DNN model. However, it is challenging to generate effective adversarial examples in… read more here.

Keywords: attack; robust generalized; adversarial examples; meta gan ... See more keywords