Topal, A. O., Chitic, I. R., & Leprevost, F. (11 May 2023). One evolutionary algorithm deceives humans and ten convolutional neural networks trained on ImageNet at image recognition. Applied Soft Computing, 143, 110397. doi:10.1016/j.asoc.2023.110397 Peer Reviewed verified by ORBi |
Chitic, I. R., Topal, A. O., & Leprevost, F. (22 March 2023). ShuffleDetect: Detecting Adversarial Images against Convolutional Neural Networks. Applied Sciences, 13 (6), 4068. doi:10.3390/app13064068 Peer Reviewed verified by ORBi |
Leprevost, F., Topal, A. O., Avdusinovic, E., & Chitic, I. R. (2022). Strategy and Feasibility Study for the Construction of High Resolution Images Adversarial Against Convolutional Neural Networks. In ACIIDS 2022: Intelligent Information and Database Systems (pp. 285-298). Springer. doi:10.1007/978-3-031-21743-2_23 Peer reviewed |
Leprevost, F., Topal, A. O., Avdusinovic, E., & Chitic, I. R. (22 October 2022). A strategy creating high-resolution adversarial images against convolutional neural networks and a feasibility study on 10 CNNs. Journal of Information and Telecommunication, 7 (1), 89-119. doi:10.1080/24751839.2022.2132586 Peer Reviewed verified by ORBi |
Chitic, I. R. (2022). Evolutionary Algorithm-based Adversarial Attacks Against Image Classification Convolutional Neural Networks [Doctoral thesis, Unilu - University of Luxembourg]. ORBilu-University of Luxembourg. https://orbilu.uni.lu/handle/10993/52582 |
Chitic, I. R., Topal, A. O., & Leprevost, F. (2021). Evolutionary Algorithm-based images, humanly indistinguishable and adversarial against Convolutional Neural Networks: efficiency and filter robustness. IEEE Access. doi:10.1109/ACCESS.2021.3131255 Peer Reviewed verified by ORBi |
Chitic, I. R., Deridder, N., Leprevost, F., & Bernard, N. (17 August 2021). Robustness of Adversarial Images against Filters. Optimization and Learning, 1443, 101-114. Peer reviewed |
Chitic, I. R., Leprevost, F., & Bernard, N. (2020). Evolutionary algorithms deceive humans and machines at image classification: An extended proof of concept on two scenarios. Journal of Information and Telecommunication. doi:10.1080/24751839.2020.1829388 Peer Reviewed verified by ORBi |
Chitic, R. I., Bernard, N., & Leprévost, F. (2020). A proof of concept to deceive humans and machines at image classification with evolutionary algorithms. In I. R. Chitic, N. Bernard, ... F. Leprévost, Proceedings of ACIIDS 2020 (pp. 467-480). Springer. Peer reviewed |