3 papers
cs.CV2024
Adversarial Examples in the Physical World: A Survey
Jiakai Wang, Xianglong Liu, Jin Hu +6
Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples, raising broad security concerns about their applications. Besides the attacks in the digit…
cs.CV2024
Improving the Transferability of Adversarial Examples by Feature Augmentation
Donghua Wang, Wen Yao, Tingsong Jiang +3
Despite the success of input transformation-based attacks on boosting adversarial transferability, the performance is unsatisfying due to the ignorance of the discrepancy across mo…
cs.CV2024
Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
Donghua Wang, Wen Yao, Tingsong Jiang +2
Object detectors have demonstrated vulnerability to adversarial examples crafted by small perturbations that can deceive the object detector. Existing adversarial attacks mainly fo…