News
AI4CCAM at at the 23rd International Conference on Security and Cryptography (SECRYPT)
AI4CCAM ended in March but it’s still on stage!
16-18 July, AI4CCAM will be attending 23rd International Conference on Security and Cryptography (SECRYPT 2026) in Porto, Portugal, the event focusing on theoretical and practical aspects of data protection, privacy, and applied cryptography.
Marwan Lazrag, Telecom SudParis, will present the recently approved Paper “Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles”: poisoning attacks against public datasets lead to major concerns, such as misclassification of perceived objects when the poisoned data is used for training and embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply over the learned models. Its impact over data augmentation models is unclear. While data augmentation reduces the likelihood of poisoning attack success, some valid questions remain.
Is data augmentation affecting the impact of poisoning attacks? Can it increase the number of poisoned samples or injected backdoors? The Paper explores some of these questions, assessing the effects of augmenting poisoned 3D point cloud datasets and validate that poisoning is able to evade the sanitizing nature of augmentation techniques when using the concrete case of Generative Adversarial Network (GAN) techniques to exemplify the case of data augmentation processing.
