Hai Jin

6

Papers

21

Total Citations

Papers (6)

Multi-Turn Jailbreaking Large Language Models via Attention Shifting

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models