3 papers
quant-ph2026
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
Junrui Zhang, Zemin Chen, Lusi Li +3
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studi…
cs.LG2026
Laplace-Bridged Randomized Smoothing for Fast Certified Robustness
Miao Lin, MD Saifur Rahman Mazumder, Feng Yu +2
Randomized Smoothing (RS) offers formal guarantees for arbitrary base classifiers but faces two key practical bottlenecks: (i) it often relies on noise-augmented training…
cs.CR2025
Heterogeneous Graph Backdoor Attack
Jiawei Chen, Lusi Li, Daniel Takabi +2
Heterogeneous Graph Neural Networks (HGNNs) excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplo…