1+1>2: A Dual-Function Defense Framework for Adversarial Example Mitigation.

Subspectrum mixup-based adversarial attack and evading defenses by structure-enhanced gradient purification.

Efficient History-Driven Adversarial Perturbation Distribution Learning in Low Frequency Domain.

Privacy-preserving dish-recommendation for food nutrition through edging computing.

ABCAttack: A Gradient-Free Optimization Black-Box Attack for Fooling Deep Image Classifiers.

Deep Learning Based Customer Preferences Analysis in Industry 4.0 Environment.

Improving the security and quality of real-time multimedia transmission in cyber-physical-social systems.