Results 11 to 20 of about 804,777 (293)
Survey of Image Adversarial Example Defense Techniques [PDF]
Jisuanji kexue yu tansuo, 2023 The rapid and extensive growth of artificial intelligence introduces new security challenges. The generation and defense of adversarial examples for deep neural networks is one of the hot spots.
LIU Ruiqi, LI Hu, WANG Dongxia, ZHAO Chongyang, LI Boyu
doaj +3 more sources
LPF-Defense: 3D adversarial defense based on frequency analysis. [PDF]
PLoS One, 2023 The 3D point clouds are increasingly being used in various application including safety-critical fields. It has recently been demonstrated that deep neural networks can successfully process 3D point clouds. However, these deep networks can be misclassified via 3D adversarial attacks intentionality designed to perturb some point cloud’s features.
Naderi H +3 more
europepmc +5 more sources
Universal attention guided adversarial defense using feature pyramid and non-local mechanisms [PDF]
Scientific ReportsDeep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, significantly hindering the development of deep learning technologies in high-security domains. A key challenge is that current defense methods often lack universality,
Jiawei Zhao +6 more
doaj +2 more sources
CoRR, 2023 The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their generation. If the generation of adversarial examples is unregulated, images within reach are no longer secure and pose
Jinwei Wang +5 more
openaire +3 more sources
Open-Set Adversarial Defense with Clean-Adversarial Mutual Learning [PDF]
International Journal of Computer Vision, 2022 Accepted by International Journal of Computer Vision (IJCV) 2022. Code will be available at https://github.com/rshaojimmy/ECCV2020-OSAD.
Vishal M Patel, Pong Chi Yuen, Rui Shao
exaly +5 more sources
Adversarial Backdoor Defense in CLIP [PDF]
CoRRMultimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks. While current backdoor defense methods primarily employ conventional data augmentation to create augmented samples aimed at feature alignment, these methods fail to capture the distinct features of backdoor samples, resulting in ...
Junhao Kuang +4 more
core +4 more sources
Text Adversarial Purification as Defense against Adversarial Attacks
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023 Accepted by ACL2023 main ...
Linyang Li, Demin Song, Xipeng Qiu
openaire +3 more sources
Deepfake Cross-Model Defense Method Based on Generative Adversarial Network [PDF]
Jisuanji gongchengTo reduce social risks caused by the abuse of deepfake technology, an active defense method against deep forgery based on a Generative Adversarial Network (GAN) is proposed. Adversarial samples are created by adding imperceptible perturbation to original
DAI Lei, CAO Lin, GUO Yanan, ZHANG Fan, DU Kangning
doaj +2 more sources
A Mask-Based Adversarial Defense Scheme
Algorithms, 2022 Adversarial attacks hamper the functionality and accuracy of deep neural networks (DNNs) by meddling with subtle perturbations to their inputs. In this work, we propose a new mask-based adversarial defense scheme (MAD) for DNNs to mitigate the negative ...
Weizhen Xu +3 more
doaj +2 more sources
Adversarial Sample Defense Method Based on Noise Dissolution [PDF]
Jisuanji gongcheng, 2022 The security problems exposed in the rapid development of the Deep Neural Network(DNN) have gradually attracted our attention.However, since adversarial examples were first defined, many adversarial attacks on DNNs have been proposed, and the complexity ...
YANG Wenxue, WU Fei, GUO Tong, XIAO Limin
doaj +1 more source