Guanmeng Xian

2 accepted papers

2026

Band Together: Untargeted Adversarial Training with Multimodal Coordination Against Evasion-Based Promotion Attacks

IJCAI 2026

Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-modal settings and mainly focus on poisoning-based threats, leaving evasion-based

Cited by 0 Scholar ↗

2026

Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment

Guanmeng Xian, Ning Yang, Philip S. Yu

IJCAI 2026

Adversarial training is effective on balanced datasets, but its robustness degrades under long-tailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose \emph{Manifold-Constrained Adversarial Training (MCAT)}, a unified framework that enforc

Cited by 0 Scholar ↗