Results 31 to 40 of about 8,712 (199)
Suppress with a Patch: Revisiting Universal Adversarial Patch Attacks against Object Detection
2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2022 Adversarial patch-based attacks aim to fool a neural network with an intentionally generated noise, which is concentrated in a particular region of an input image. In this work, we perform an in-depth analysis of different patch generation parameters, including initialization, patch size, and especially positioning a patch in an image during training ...
Pavlitskaya, Svetlana +5 more
openaire +3 more sources
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
CoRR, 2022 accepted at ICLR ...
Maksym Yatsura +4 more
openaire +3 more sources
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
, 2022 Deep learning has substantially boosted the performance of Monocular Depth Estimation (MDE), a critical component in fully vision-based autonomous driving (AD) systems (e.g., Tesla and Toyota). In this work, we develop an attack against learning-based MDE.
Zhiyuan Cheng 0010 +6 more
openaire +2 more sources
A Momentum-Based Local Face Adversarial Example Generation Algorithm
Algorithms, 2022 Small perturbations can make deep models fail. Since deep models are widely used in face recognition systems (FRS) such as surveillance and access control, adversarial examples may introduce more subtle threats to face recognition systems. In this paper,
Dapeng Lang +3 more
doaj +1 more source
CopyCAT: Taking Control of Neural Policies with Constant Attacks [PDF]
, 2020 We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an agent into following an outsider's policy. It is pre-computed, therefore fast
Geist, Matthieu +2 more
core +1 more source
Physical Passive Patch Adversarial Attacks on Visual Odometry Systems
, 2023 Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs ...
Yaniv Nemcovsky +3 more
openaire +2 more sources
Unified Adversarial Patch for Cross-modal Attacks in the Physical World
2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023 10 pages, 8 figures, accepted by ...
Xingxing Wei 0001 +3 more
openaire +2 more sources
IPatch: a remote adversarial patch
Cybersecurity, 2023 Applications such as autonomous vehicles and medical screening use deep learning models to localize and identify hundreds of objects in a single frame. In the past, it has been shown how an attacker can fool these models by placing an adversarial patch ...
Yisroel Mirsky
doaj +1 more source
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.
Jarhinbek Rasol +7 more
doaj +1 more source
Detecting the Unexpected via Image Resynthesis
, 2019 Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training.
Fua, Pascal +3 more
core +1 more source