Results 101 to 110 of about 619 (184)

URAdv: A Novel Framework for Generating Ultra-Robust Adversarial Patches Against UAV Object Detection

Mathematics
In recent years, deep learning has been extensively deployed on unmanned aerial vehicles (UAVs), particularly for object detection. As the cornerstone of UAV-based object detection, deep neural networks are susceptible to adversarial attacks, with ...
Hailong Xi, Le Ru, Jiwei Tian, Bo Lu, Shiguang Hu, Wenfei Wang, Xiaohui Luan   +6 more
doaj   +1 more source

An Adaptive Physical-World Adversarial Patch for Remote Sensing Image Object Detection Models Considering the Structural Characteristics

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Remote sensing image object detection represents a typical application in the field of remote sensing image processing. Rapid advancements in artificial intelligence have established deep learning as a prevalent method for detecting critical targets ...
Xichen Xing, Xiong Xu, Qian Shi, Yanmin Jin, Chao Wang   +4 more
doaj   +1 more source

RNAF: ResilienceNet Adversarial Framework Using Deep Reinforcement Learning for Adversarial Attacks on Digital Images

IEEE Access
Adversarial attack is a key concern for state-of-the-art artificial intelligence (AI), especially those used in image classification and computer vision.
Kainat Rizwan, Muhammad Asif Habib, Salman Raza, Mudassar Ahmad   +3 more
doaj   +1 more source

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   +1 more source

Universal and transferable attacks on pathology foundation models using microscopic perturbations. [PDF]

Light Sci Appl
Wang Y, Yang X, Shen CY, Dong S, Pillar N, Ozcan A.   +5 more
europepmc   +1 more source

Evaluating gait system vulnerabilities through PPO and GAN-generated adversarial attacks. [PDF]

Sci Rep
Saoudi EM, Jaafari J, Jai Andaloussi S.
europepmc   +1 more source

Physics-Aware Spatiotemporal Consistency for Transferable Defense of Autonomous Driving Perception. [PDF]

Sensors (Basel)
Liu Y, Nie Z, Yu T, Chen M, Yao Z, Lu J, Peng L, Fan F.   +7 more
europepmc   +1 more source

Attentional semantic attack for enhancing adversarial samples transferability. [PDF]

Sci Rep
Wang P, Liu J.
europepmc   +1 more source

Symmetry-Driven Multimodal Adversarial Attacks: An Information-Theoretic Perspective on Cross-Modal Invariance and Robustness. [PDF]

Entropy (Basel)
Wei J, Wang X, Xu L, Li Y.
europepmc   +1 more source

Evaluating the Adversarial Robustness and Clinical Safety of Quantized Hierarchical Transformers for Edge-Based Malaria Microscopy. [PDF]

Sensors (Basel)
Hasan U, Alghamdi TG, Nayeem MA.
europepmc   +1 more source