Results 51 to 60 of about 505,564 (200)
Query complexity of adversarial attacks
CoRR, 2020 There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask. Using this point of view we investigate how many queries the adversary needs to make to design an attack that is ...
Grzegorz Gluch, Rüdiger L. Urbanke
openaire +3 more sources
Direction-aggregated Attack for Transferable Adversarial Examples [PDF]
, 2022 Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters are available ...
Pei, Yulong +7 more
core +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 +3 more sources
, 2020 Observational studies have suggested that accelerated surgery is associated with improved outcomes in patients with a hip fracture.
(HIP ATTACK Investigators), Landoni G.
core +1 more source
Launching Adversarial Attacks against Network Intrusion Detection Systems for IoT [PDF]
, 2021 As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought.
William J. Buchanan +13 more
core +1 more source
Secure machine learning against adversarial samples at test time
EURASIP Journal on Information Security, 2022 Deep neural networks (DNNs) are widely used to handle many difficult tasks, such as image classification and malware detection, and achieve outstanding performance.
Jing Lin, Laurent L. Njilla, Kaiqi Xiong
doaj +1 more source
Adversarial Attack Transferability Enhancement Algorithm Based on Input Channel Splitting [PDF]
Jisuanji gongcheng, 2023 The Deep Neural Network(DNN) has been widely used in face recognition, automatic driving, and other scenarios;however, it is vulnerable to attacks by adversarial samples.Methods by which adversarial samples are generated can be classified into white-box ...
ZHENG Desheng, CHEN Jixin, ZHOU Jing, KE Wuping, LU Chao, ZHOU Yong, QIU Qian
doaj +1 more source
Timbre-reserved Adversarial Attack in Speaker Identification [PDF]
, 2023 As a type of biometric identification, a speaker identification (SID) system is confronted with various kinds of attacks. The spoofing attacks typically imitate the timbre of the target speakers, while the adversarial attacks confuse the SID system by ...
Guo, Pengcheng +4 more
core +1 more source
Adversarial attacks against supervised machine learning based network intrusion detection systems.
PLoS ONE, 2022 Adversarial machine learning is a recent area of study that explores both adversarial attack strategy and detection systems of adversarial attacks, which are inputs specially crafted to outwit the classification of detection systems or disrupt the ...
Ebtihaj Alshahrani +3 more
doaj +2 more sources
Perceptually Constrained Adversarial Attacks
CoRR, 2021 Motivated by previous observations that the usually applied $L_p$ norms ($p=1,2,\infty$) do not capture the perceptual quality of adversarial examples in image classification, we propose to replace these norms with the structural similarity index (SSIM) measure, which was developed originally to measure the perceptual similarity of images.
Muhammad Zaid Hameed +1 more
openaire +3 more sources