Bin Ma

The Hong Kong University of Science and Technology (Guangzhou)

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Architecture Design (Transformers, SSMs, MoE) (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Yuxiang Zhang (1)Enyan Dai (1)

Papers (1)

Mar 5, 2026

1w ago

Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks

Clean-label graph backdoor attacks are now significantly more effective: BA-Logic can successfully poison GNNs by manipulating their inner prediction logic, even without modifying training labels.

Yuxiang Zhang, Bin Ma, Enyan Dai

Architecture Design (Transformers, SSMs, MoE)Red-Teaming & Adversarial Robustness

Search

Bin Ma

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)