7 papers
JDCNet: Confidence-Gated Privileged-Modality Distillation for Cost-Preserving X-ray Inference
Bo Ma, Jinsong Wu, Weiqi Yan +2
We study a systems-level visual inference problem: using an expensive privileged modality during training while preserving a fixed-cost, single-modality deployment path. We present…
COREY: Entropy-Guided Runtime Chunk Scheduling for Selective Scan Kernels
Bo Ma, Jinsong Wu, Weiqi Yan
Mamba selective state space models (SSMs) provide linear-time sequence modeling but remain sensitive to selective-scan chunk scheduling. We present COREY, a \emph{concept-and-feasi…
PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences
Bo Ma, Weiqi Yan, Jinsong Wu
We propose PPEDCRF, a calibrated selective perturbation framework that protects \emph{background-based location privacy} in released video frames against gallery-based retrieval at…
BodhiPromptShield: Pre-Inference Prompt Mediation for Suppressing Privacy Propagation in LLM/VLM Agents
Bo Ma, Jinsong Wu, Weiqi Yan
In LLM/VLM agents, prompt privacy risk propagates beyond a single model call because raw user content can flow into retrieval queries, memory writes, tool calls, and logs. Existing…
Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
Bo Ma, Wei Qi Yan, Jinsong Wu
Learning systems that preserve privacy often inject noise into hierarchical visual representations; a central challenge is to \emph{model} how such perturbations align with a decla…
REAEDP: Entropy-Calibrated Differentially Private Data Release with Formal Guarantees and Attack-Based Evaluation
Bo Ma, Jinsong Wu, Wei Qi Yan
Sensitive data release is vulnerable to output-side privacy threats such as membership inference, attribute inference, and record linkage. This creates a practical need for release…