9 papers
HarmQ: Harmonic Backdoor Attacks Against Quantum Neural Networks
Junrui Zhang, Zemin Chen, Chunsheng Xin +2
The paper proposes HarmQ, a backdoor attack for quantum neural networks that embeds low‑frequency sinusoidal (harmonic) triggers compatible with the Fourier bias of parameterized q…
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
Junrui Zhang, Zemin Chen, Lusi Li +3
The paper introduces Q-DIBA, an input‑aware dynamic backdoor attack for quantum neural networks that jointly trains a classical trigger generator with the QNN and uses an ensemble…
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…
DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
Xiaozuo Shen, Yifei Cai, Rui Ning +2
The widespread adoption of Vision Transformers (ViTs) elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Exis…
RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
Miao Lin, Feng Yu, Rui Ning +6
Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world sce…
Deep Incomplete Multi-View Clustering via Hierarchical Imputation and Alignment
Yiming Du, Ziyu Wang, Jian Li +2
Incomplete multi-view clustering (IMVC) aims to discover shared cluster structures from multi-view data with partial observations. The core challenges lie in accurately imputing mi…