collaborators

5 papers

cs.CR2026

DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption

Chang Liu, Yuni Lai, Mingyue Cui +5

Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign en…

cs.CR2025

Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models

Xiaoyu Xue, Yuni Lai, Chenxi Huang +4

The emergence of graph foundation models (GFMs), particularly those incorporating language models (LMs), has revolutionized graph learning and demonstrated remarkable performance o…

cs.LG2025

Provably Robust Adaptation for Language-Empowered Foundation Models

Yuni Lai, Xiaoyu Xue, Linghui Shen +5

Language-empowered foundation models (LeFMs), such as CLIP and GraphCLIP, have transformed multimodal learning by aligning visual (or graph) features with textual representations,…

cs.LG2025

Towards Robust Graph Structural Learning Beyond Homophily via Preserving Neighbor Similarity

Yulin Zhu, Yuni Lai, Xing Ai +7

Despite the tremendous success of graph-based learning systems in handling structural data, it has been widely investigated that they are fragile to adversarial attacks on homophil…

cs.LG2025

AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing

Yuni Lai, Yulin Zhu, Yixuan Sun +6

Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness. Certified robustness via randomized smoothing offers provable guarant…