Shengye Pang — accepted AI-conference papers

2026

Mask-Guided Hybrid Triggers for Robust Clean-Label Backdoor Attacks

Shengye Pang, Xiangyu Ji, Jungang Yang, Song Yang, Guobing Zou

IJCAI 2026

Clean-label backdoor attacks pose significant security threats to deep neural networks by injecting triggers without altering ground-truth labels. However, existing methods face a fundamental dilemma: sample-agnostic triggers are robust but easily detectable, while sample-specific triggers offer sup

Cited by 0 Scholar ↗

2026

Subspace-Aware Graph Construction and Contrastive Alignment for Multimodal Recommendation with Large Language Models

Haodong Li, Lianyong Qi, Weiming Liu, Fan Wang, Chong Li, Shengye Pang +5

AAAI 2026technical

Multimedia content offers additional context for recommender systems to better understand user interests. Existing studies on multimodal recommendation primarily focus on constructing item-item semantic graphs. However, most of these methods capture only shallow semantic structures based on feature

Cited by 0 Source ↗PDF ↗Scholar ↗