Results 21 to 30 of about 5,574 (249)

SSIM-Based Autoencoder Modeling to Defeat Adversarial Patch Attacks [PDF]

Sensors
Object detection systems are used in various fields such as autonomous vehicles and facial recognition. In particular, object detection using deep learning networks enables real-time processing in low-performance edge devices and can maintain high ...
Seungyeol Lee, Seongwoo Hong, Gwangyeol Kim, Jaecheol Ha   +3 more
doaj   +2 more sources

An Adaptive Adversarial Patch-Generating Algorithm for Defending against the Intelligent Low, Slow, and Small Target

Remote Sensing, 2023
The “low, slow, and small” target (LSST) poses a significant threat to the military ground unit. It is hard to defend against due to its invisibility to numerous detecting devices.
Yuelei Xu, Zhaoxiang Zhang, Weijia Feng   +2 more
exaly   +3 more sources

Benchmarking Adversarial Patch Selection and Location

Mathematics
Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5×108 forward passes on ImageNet validation images.
Shai Kimhi, Moshe Kimhi, Avi Mendelson
doaj   +3 more sources

“Just a Patch”: Imperceptible Image Patch Generation for Adversarial Inference

IEEE Access
Image classification models, based on deep neural networks, are vulnerable to adversarial input poisoning attacks where a maliciously crafted input results in incorrect predictions.
Debasmita Manna, Somanath Tripathy, Bruhadeshwar Bezawada, Indrakshi Ray   +3 more
doaj   +2 more sources

Adversarial YOLO: Defense Human Detection Patch Attacks via Detecting Adversarial Patches

CoRR, 2021
9 pages, 7 ...
Nan Ji, YanFei Feng, Haidong Xie, Xueshuang Xiang, Naijin Liu   +4 more
openaire   +2 more sources

Defense against Adversarial Patch Attacks for Aerial Image Semantic Segmentation by Robust Feature Extraction

Remote Sensing, 2023
Deep learning (DL) models have recently been widely used in UAV aerial image semantic segmentation tasks and have achieved excellent performance. However, DL models are vulnerable to adversarial examples, which bring significant security risks to safety ...
Zhen Wang, Buhong Wang, Chuanlei Zhang, Yaohui Liu   +3 more
doaj   +1 more source

TPatch: A Triggered Physical Adversarial Patch

CoRR, 2023
Appeared in 32nd USENIX Security Symposium (USENIX Security 23)
Wenjun Zhu, Xiaoyu Ji 0001, Yushi Cheng, Shibo Zhang, Wenyuan Xu 0001   +4 more
openaire   +3 more sources

Adversarial Training Against Location-Optimized Adversarial Patches [PDF]

, 2020
20 pages, 6 tables, 4 figures, 2 algorithms, European Conference on Computer Vision Workshops ...
Sukrut Rao, David Stutz, Bernt Schiele
openaire   +4 more sources

Certified Defenses for Adversarial Patches

CoRR, 2020
International Conference on Learning Representations, ICLR ...
Chiang, Ping-yeh, Ni, Renkun, Abdelkader, Ahmed, Zhu, Chen, Studer, Christoph; id_orcid0000-0001-8950-6267, Goldstein, Tom   +5 more
openaire   +4 more sources

Generating Visually Realistic Adversarial Patch

CoRR, 2023
Deep neural networks (DNNs) are vulnerable to various types of adversarial examples, bringing huge threats to security-critical applications. Among these, adversarial patches have drawn increasing attention due to their good applicability to fool DNNs in the physical world.
Xiaosen Wang, Kunyu Wang
openaire   +2 more sources