Results 41 to 50 of about 1,236,597 (154)
CoRR, 2022 Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing inputs, often using a model's loss function to craft such perturbations.
Thomas Cilloni +2 more
openaire +2 more sources
Restricted Black-Box Adversarial Attack Against DeepFake Face Swapping [PDF]
IEEE Transactions on Information Forensics and Security, 2022 DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an entirely different person. In order to prevent this fraud, some researchers
Junhao Dong +3 more
semanticscholar +1 more source
Adversarial Patch Attack on Multi-Scale Object Detection for UAV Remote Sensing Images
Remote Sensing, 2022 Although deep learning has received extensive attention and achieved excellent performance in various scenarios, it suffers from adversarial examples to some extent. In particular, physical attack poses a greater threat than digital attack.
Yichuang Zhang +6 more
doaj +1 more source
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness [PDF]
European Conference on Computer Vision, 2022 Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images.
Jindong Gu +3 more
semanticscholar +1 more source
CoRR, 2021 Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream. In this paper, we formalize the online adversarial attack problem, emphasizing two key elements found in real-world use-cases: attackers must operate under partial knowledge of the target model ...
Andjela Mladenovic +6 more
openaire +3 more sources
A Hybrid Adversarial Attack for Different Application Scenarios
Applied Sciences, 2020 Adversarial attack against natural language has been a hot topic in the field of artificial intelligence security in recent years. It is mainly to study the methods and implementation of generating adversarial examples. The purpose is to better deal with
Xiaohu Du +6 more
doaj +1 more source
Physical Adversarial Attack Meets Computer Vision: A Decade Survey [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern.
Hui Wei +7 more
semanticscholar +1 more source
Deflecting Adversarial Attacks
CoRR, 2020 There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks by causing the attacker to produce an input that semantically resembles the attack's target class.
Yao Qin 0001 +4 more
openaire +2 more sources
AdvDrop: Adversarial Attack to DNNs by Dropping Information [PDF]
IEEE International Conference on Computer Vision, 2021 Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects ...
Ranjie Duan +5 more
semanticscholar +1 more source
Augmented Lagrangian Adversarial Attacks [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 ICCV 2021 (Poster).
Jérôme Rony +3 more
openaire +2 more sources