Bin Yi
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Research Timeline
2026
Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition
The paper introduces Distributed Semantic Recomposition (DSR), a novel cross-modal jailbreaking framework that bypasses existing safety filters by decomposing harmful intent into benign input components, achieving high attack success rates with low input toxicity.
Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving
This study successfully demonstrates that federated learning can achieve prediction accuracy comparable to centralized modeling for multi-center sepsis prediction while fundamentally preserving patient data privacy.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CRRecentJun 3, 2026
Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving
Xixi Tian, Di Wu, Xiang Liu, Yiziting Zhu +3 more
This study successfully demonstrates that federated learning can achieve prediction accuracy comparable to centralized modeling for multi-center sepsis prediction while fundamentally preserving patien…
View →
cs.CRRecentJun 1, 2026