Search Results for author:
Found 13 papers, 1 papers with code
Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
These perturbations are cyclically applied to various parts of a pedestrian's clothing to facilitate multi-view black-box physical attacks on infrared pedestrian detectors.
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World
Using Particle Swarm Optimization, we optimize two Bezier curves and employ cold patches in the physical realm to introduce perturbations, creating infrared curve patterns for physical sample generation.
Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world
The TOUAP employs a two-stage optimization process: firstly, PSO optimizes an irregular polygonal infrared patch to attack the infrared detector; secondly, the color QR code is optimized, and the shape information of the infrared patch from the first stage is used as a mask.
Impact of Light and Shadow on Robustness of Deep Neural Networks
Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection.
Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical World
Infrared imaging systems have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern.
Adversarial Color Projection: A Projector-based Physical Attack to DNNs
In the digital environment, we achieve an attack success rate of 97. 60% on a subset of ImageNet, while in the physical environment, we attain an attack success rate of 100% in the indoor test and 82. 14% in the outdoor test.
Adversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNs
We evaluate the proposed method in three aspects: effectiveness, stealthiness, and robustness.
Impact of Colour Variation on Robustness of Deep Neural Networks
Whereas recent advances have shown their vulnerability to manual digital perturbations in the input data, namely adversarial attacks.
Impact of Scaled Image on Robustness of Deep Neural Networks
The accuracy of the networks is remarkably influenced by the data distribution of their training dataset.
Adversarial Color Film: Effective Physical-World Attack to DNNs
It is well known that the performance of deep neural networks (DNNs) is susceptible to subtle interference.
Adversarial Zoom Lens: A Novel Physical-World Attack to DNNs
In a digital environment, we construct a data set based on AdvZL to verify the antagonism of equal-scale enlarged images to DNNs.
Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs
It realizes robust and covert physical attack by using low-cost laser equipment.
Adversarial Neon Beam: A Light-based Physical Attack to DNNs
Moreover, we validate the robustness of our approach by successfully attacking advanced DNNs with a success rate of over 75% in all cases.
