7 papers
Occluding the Solution Space: Planner-Agnostic Adversarial Attacks on Tolerance-Aware Manipulation
Keke Tang, Tianyu Hao, Weilong Peng +5
Adversarial attacks on motion planning are crucial for evaluating and quantifying the intrinsic robustness of robotic manipulation. However, existing approaches are typically limit…
Rethinking Transferable Adversarial Attacks on Point Clouds from a Compact Subspace Perspective
Keke Tang, Xianheng Liu, Weilong Peng +5
Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen ar…
Optimal Transport-Induced Samples against Out-of-Distribution Overconfidence
Keke Tang, Ziyong Du, Xiaofei Wang +3
Deep neural networks (DNNs) often produce overconfident predictions on out-of-distribution (OOD) inputs, undermining their reliability in open-world environments. Singularities in…
Transferable and Undefendable Point Cloud Attacks via Medial Axis Transform
Keke Tang, Yuze Gao, Weilong Peng +3
Studying adversarial attacks on point clouds is essential for evaluating and improving the robustness of 3D deep learning models. However, most existing attack methods are develope…
Cage-Based Deformation for Transferable and Undefendable Point Cloud Attack
Keke Tang, Ziyong Du, Weilong Peng +4
Adversarial attacks on point clouds often impose strict geometric constraints to preserve plausibility; however, such constraints inherently limit transferability and undefendabili…
EOOD: Entropy-based Out-of-distribution Detection
Guide Yang, Chao Hou, Weilong Peng +4
Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained o…