Entity · paper

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

paperactiveprovisional

assessing-the-operational-impact-of-poisoning-attacks-over-augmented-3d-point-cloud-public-datasets-for-connected-and-autonomous-vehicles-6bd42621

·1 events·first seen Jul 8, 2026

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

Co-occurring entities

Generative Adversarial Networks

More like this (12)

Human-Vehicle Interaction Benchmark 2026 State of AI Traffic and Cyberthreat Benchmark Report Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution Waymo Open Dataset ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications Fixed-Payload Poisoning Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation Waymo Open Motion Dataset Where Does the Answer Come From? Benchmarking View-Level Visual Evidence Identification in Multi-View MLLMs for Autonomous Driving Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation ToxiREX: A Dataset on Toxic REasoning in ConteXt

Recent events (1)

4arXiv · cs.LG·Jul 8, 2026·source ↗

Poisoning attacks persist through GAN-based data augmentation in 3D point cloud datasets for autonomous vehicles

A new arXiv paper investigates whether data augmentation can neutralize poisoning attacks on 3D point cloud datasets used in connected and autonomous vehicle (CAV) perception systems. The authors find that poisoning survives GAN-based augmentation pipelines, propagates into augmented datasets, and continues to degrade downstream classifier decisions. Experimental materials including tools, datasets, and classifiers are released publicly to support reproducibility.

Evaluation and Benchmarking AI Safety Research Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles Generative Adversarial Networks