Results 41 to 50 of about 527,315 (106)

A Distributed Biased Boundary Attack Method in Black-Box Attack

Applied Sciences, 2021
The adversarial samples threaten the effectiveness of machine learning (ML) models and algorithms in many applications. In particular, black-box attack methods are quite close to actual scenarios.
Fengtao Xiang, Jiahui Xu, Wanpeng Zhang, Weidong Wang   +3 more
doaj   +1 more source

Wasserstein Adversarial Robustness [PDF]

, 2020
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to ``small, imperceptible'' perturbations known as adversarial attacks.
Wu, Kaiwen
core  

Adversarial accuracy per th for L_∞ attack.

, 2022
Adversarial accuracy per th for L∞ attack.
Danilo Vasconcellos Vargas (12418891), Shashank Kotyan (12418888)   +1 more
core   +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, Xie, Lei, Zhang, Li, Wang, Qing, Yao, Jixun   +4 more
core  

Adversarial accuracy per th for L₀ attack.

, 2022
Adversarial accuracy per th for L0 attack.
Danilo Vasconcellos Vargas (12418891), Shashank Kotyan (12418888)   +1 more
core   +1 more source

Adversarial retraining attack of asynchronous advantage actor-critic based pathfinding

, 2021
Adversarial retraining attack of asynchronous advantage actor-critic based ...
C Liang (13462671), N Wenjia (13462659), W Shuoru (13462665), L He (13462668), C Qi Alfred (13462677), C Tong (13462650), L Jiqiang (13462653), L Gang (13462674), X Yingxiao (13462656), T Endong (13462662)   +9 more
core  

Multi-Level Chinese Adversarial Example Generation Method Based on Glyph and Semantic [PDF]

Jisuanji gongcheng
Deep neural network language models are vulnerable to adversarial example attacks during application. To address this issue, adversarial examples are typically generated by adding minor perturbations to the original samples to mislead the model into ...
SUN Yu, WANG Hongjie, DU Yanhui, LIU Nan
doaj   +1 more source

Deep Reinforcement Learning-Based Adversarial Attack and Defense in Industrial Control Systems

Mathematics
Adversarial attacks targeting industrial control systems, such as the Maroochy wastewater system attack and the Stuxnet worm attack, have caused significant damage to related facilities.
Mun-Suk Kim
doaj   +1 more source

AdverPaint: Inpainting-Based Adversarial Attack on Face Recognition Systems

IEEE Access
Although adversarial attacks on face recognition systems require both high attack effectiveness and visual stealthiness, existing adversarial attacks often introduce noticeable discrepancies that make them susceptible to detection and purification ...
Soo-Hyun Lee, Hyun Jun Yook, Ga San Jhun, Yoon Hyuck Cho, Min Kyu Choi, Youn Kyu Lee   +5 more
doaj   +1 more source

Benign-salient Region Based End-to-End Adversarial Malware Generation Method [PDF]

Jisuanji kexue
Malware detection methods combining visualization techniques and deep learning have gained widespread attention due to their high accuracy and low cost.However,deep learning models are vulnerable to adversarial attacks,where intentional small-scale ...
YUAN Mengjiao, LU Tianliang, HUANG Wanxin, HE Houhan
doaj   +1 more source