Cheng Wang

The paper proposes a novel CRT-based asymptotically perfect Disjunctive Hierarchical Secret Sharing (DHSS) scheme that overcomes security and information rate limitations of existing methods.

PrismWF introduces a multi-granularity patch-based Transformer to significantly improve website fingerprinting attacks by effectively modeling complex, mixed-traffic patterns from multi-tab browsing sessions.

The paper proposes two new asymptotically ideal and secure Hierarchical Secret Sharing (HSS) schemes, disjunctive and conjunctive, utilizing the Chinese Remainder Theorem (CRT) over an integer ring and one-way functions.

The paper introduces a novel, asymptotically ideal Conjunctive Hierarchical Secret Sharing (CHSS) scheme using the Chinese Remainder Theorem (CRT) for polynomial rings, achieving high security and an optimal information rate.

Styx is a novel framework that enhances data privacy and security in collaborative data processing, such as joint AI training, by integrating sticky policies with Trusted Execution Environments (TEEs).

The paper proposes a lightweight, self-adaptive framework using LoRA to efficiently extract and aggregate radio frequency fingerprints for robust open-set authentication in dynamic wireless environments.

The paper introduces extsc{Spore}, a novel, training-free, and highly efficient privacy extraction attack that targets sensitive information stored in the memory of LLM agents during inference, outperforming existing state-of-the-art methods.

PoisonCap introduces a new 'poison' capability format for CHERI systems to provide efficient, strict use-after-free and initialization safety, surpassing existing temporal safety solutions.

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functions.

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Models (LVLMs).

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving state-of-the-art performance with reduced latency.

This paper proposes and validates a novel hardware architecture, ITP-STDP, to significantly reduce the energy consumption and hardware overhead associated with training Spiking Neural Networks (SNNs).

This paper investigates the thermal constraints of deploying AI compute infrastructure in space, comparing GPUs and compute-in-memory (CIM) accelerators using a co-design methodology.