.png){kind=icon}
返回
Space-Constrained Random Sparse Adversarial Attack
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129436.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Adversarial attacks aim to deceive deep neural networks (DNNs) by introducing carefully designed perturbations. Traditional black-box methods often produce large-scale perturbations, reducing their practicality in real-world scenarios. Asa result, sparse adversarial attacks emerged to improve invisibility and effectiveness by minimizing the number of disturbed pixels, but a major challenge lies in balancing sparsity with attack success. To address this challenge, we propose a novel Space-Constrained Random Sparse Adversarial Attack (SRSA), which focuses on space most influential to the model's decision-making process. SRSA employs a weighted sampling strategy to dynamically update perturbation scores for each space, prioritizing areas with higher impact. A heuristic search algorithm is then applied to precisely target pixels within the selected space, achieving both sparsity and effectiveness. Experimental results demonstrate that SRSA outperforms state-of-theart black-box sparse adversarial attacks, such as Sparse-RS, SA-MOO, SAPF, and Homotopy Attack, on DNNs trained on ImageNet. Specifically, SRSA reduces the perturbation range and magnitude by approximately 20% compared to baseline methods. Moreover, compared to the optimal query-based black-box attack method, Square Attack, SRSA achieves a higher attack success rate while modifying 30% fewer pixels. These results demonstrate that SRSA enhances attack efficiency and effectiveness by incorporating local information into the perturbation search process.
Keyword:
Black-box attack
Constrained attack space
Adversarial perturbation
Random noise
Sampling optimization
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.6W
机构
引用论文
.png){kind=icon}
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Testing the concurrent validity of a naturalistic upper extremity reaching task测试自然主义上肢到达任务的同时有效性
OAAI
OAAI分享收藏
Categorical Perception of Speech by Children With Specific Language Impairments具有特定语言障碍的儿童对语音的分类感知OAAI
OAAI分享收藏
查看更多内容