1 citations · 3 across the 16 of their papers we have counts for
7 papers · 1 filter
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…
Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
Xiao Yang, Yuni Lai, Gaolei Li +4
Semantic Communication (SC) backdoor attacks aim to utilize triggers to manipulate the system into producing predetermined outputs via backdoored shared knowledge. Current SC backd…
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…
Collective Certified Robustness against Graph Injection Attacks
Yuni Lai, Bailin Pan, Kaihuang Chen +2
We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading t…
Black-Box Attacks against Signed Graph Analysis via Balance Poisoning
Jialong Zhou, Yuni Lai, Jian Ren +1
Signed graphs are well-suited for modeling social networks as they capture both positive and negative relationships. Signed graph neural networks (SGNNs) are commonly employed to p…
Coupled-Space Attacks against Random-Walk-based Anomaly Detection
Yuni Lai, Marcin Waniek, Liying Li +5
Random Walks-based Anomaly Detection (RWAD) is commonly used to identify anomalous patterns in various applications. An intriguing characteristic of RWAD is that the input graph ca…