PulseAugur
EN
LIVE 08:05:17

Poisoning attacks evade data augmentation in 3D point cloud datasets for AVs

A new research paper investigates the impact of poisoning attacks on augmented 3D point cloud datasets, particularly for connected and autonomous vehicles. The study finds that data augmentation techniques, such as Generative Adversarial Networks (GANs), do not fully mitigate the effects of poisoning. Instead, poisoning can evade these sanitizing methods, propagate through augmented datasets, and ultimately alter the decisions made by classifiers. AI

IMPACT Highlights potential vulnerabilities in AI models used for autonomous systems, underscoring the need for robust data security and validation.

RANK_REASON Research paper published on arXiv detailing a novel finding about data poisoning and augmentation.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Poisoning attacks evade data augmentation in 3D point cloud datasets for AVs

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano, Joaquin Garcia-Alfaro ·

    Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

    arXiv:2607.06484v1 Announce Type: cross Abstract: Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered late…

  2. arXiv cs.LG TIER_1 English(EN) · Joaquin Garcia-Alfaro ·

    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 (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply…