Results 21 to 30 of about 7,737 (292)
CoRR, 2023 In response to the rapidly evolving nature of adversarial attacks against visual classifiers, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is unrealistic, as the environment in which the defense system operates is dynamic.
Qian Wang 0001 +8 more
openaire +2 more sources
Adversarial Attacks and Defenses
ACM SIGKDD Explorations Newsletter, 2021 Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where the perturbations are almost imperceptible to humans, but can cause models to make wrong predictions.
Ninghao Liu 0001 +4 more
openaire +2 more sources
Demotivate Adversarial Defense in Remote Sensing [PDF]
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021 Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection. However, these algorithms are extremely sensitive to over-fitting, domain change and adversarial examples specifically designed to fool them.
Adrien Chan-Hon-Tong +2 more
openaire +2 more sources
Open-Set Adversarial Defense [PDF]
, 2020 Accepted by ECCV ...
Rui Shao 0001 +3 more
openaire +2 more sources
Attacking Adversarial Attacks as A Defense
CoRR, 2021 It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
Boxi Wu +8 more
openaire +2 more sources
Adversarial Ranking Attack and Defense [PDF]
, 2020 Deep Neural Network (DNN) classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-explored. In this paper, we propose two attacks against deep ranking systems, i.e., Candidate Attack and Query Attack, that can ...
Mo Zhou +4 more
openaire +2 more sources
Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples. [PDF]
Sensors (Basel)Adversarial attacks on large-scale vision–language foundation models, such as the contrastive language–image pretraining (CLIP) model, can significantly degrade performance across various tasks by generating adversarial examples that are ...
Nakajima T +4 more
europepmc +2 more sources
Adversarial Defenses via a Mixture of Generators [PDF]
, 2021 In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and designing methods to counter the effects of adversarial examples.
Maciej Zelaszczyk, Jacek Mandziuk
openaire +2 more sources
, 2023 This paper presents a robust adversarial defense mechanism, Noisy-Defense Variational Auto-Encoder (ND-VAE), that combines the strengths of Nouveau VAE (NVAE) and Defense-VAE to effectively eliminate adversarial attacks from contaminated images.
Jalalinour, Shayan, Rekabdar, Banafsheh
core +1 more source
Survey on adversarial attacks and defense of face forgery and detection
网络与信息安全学报, 2023 Face forgery and detection has become a research hotspot.Face forgery methods can produce fake face images and videos.Some malicious videos, often targeting celebrities, are widely circulated on social networks, damaging the reputation of victims and ...
Shiyu HUANG, Feng YE, Tianqiang HUANG, Wei LI, Liqing HUANG, Haifeng LUO
doaj +3 more sources