19 citations · 48 across the 22 of their papers we have counts for
23 papers
Diversity Combining for Multi-Path LLM Reasoning
Guangsheng Yu, Litianyi Zhang, Qin Wang +5
Multi-path reasoning methods such as self-consistency (SC) sample reasoning paths and choose the most frequent answer. However, their gains quickly plateau as increases, an…
Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
Mingyuan Li, Guangsheng Yu, Xu Wang +1
Methods for improving knowledge use in large language models typically fall into two regimes. Non-parametric retrieval offers flexible access to external knowledge, but adds retrie…
Knows: Agent-Native Structured Research Representations
Guangsheng Yu, Xu Wang
Research artifacts are distributed primarily as reader-oriented documents like PDFs. This creates a bottleneck for increasingly agent-assisted and agent-native research workflows,…
Clawed and Dangerous: Can We Trust Open Agentic Systems?
Shiping Chen, Qin Wang, Guangsheng Yu +2
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and e…
PlanTwin: Privacy-Preserving Planning Abstractions for Cloud-Assisted LLM Agents
Guangsheng Yu, Qin Wang, Rui Lang +2
Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordinating tools and guiding execution over local environments. In many deployment…
Client-Cooperative Split Learning
Haiyu Deng, Yanna Jiang, Guangsheng Yu +5
Model training is increasingly offered as a service for resource-constrained data owners to build customized models. Split Learning (SL) enables such services by offloading trainin…
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
Yanna Jiang, Delong Li, Haiyu Deng +4
Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable…
SoK: Credential-Based Trust Management in Decentralized Ledger Systems
Yanna Jiang, Haiyu Deng, Qin Wang +6
Trust management systems (TMS) are crucial for managing trust in distributed environments. The rise of decentralized systems and blockchain has sparked interest in credential-based…
ZAPS: A Zero-Knowledge Proof Protocol for Secure UAV Authentication with Flight Path Privacy
Shayesta Naziri, Xu Wang, Guangsheng Yu +2
The increasing deployment of Unmanned Aerial Vehicles (UAVs) for military, commercial, and logistics applications has raised significant concerns regarding flight path privacy. Con…
SoK: Semantic Privacy in Large Language Models
Baihe Ma, Yanna Jiang, Xu Wang +8
As Large Language Models (LLMs) are increasingly deployed in sensitive domains, traditional data privacy measures prove inadequate for protecting information that is implicit, cont…
CAN-Trace Attack: Exploit CAN Messages to Uncover Driving Trajectories
Xiaojie Lin, Baihe Ma, Xu Wang +4
Driving trajectory data remains vulnerable to privacy breaches despite existing mitigation measures. Traditional methods for detecting driving trajectories typically rely on map-ma…
PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking
Haiyu Deng, Yanna Jiang, Guangsheng Yu +5
Our evaluation shows that PoLO achieves \textbf{99\%} watermark detection accuracy for ownership verification, while preserving data privacy and cutting verification costs to just…
BlockFUL: Enabling Unlearning in Blockchained Federated Learning
Xiao Liu, Mingyuan Li, Xu Wang +5
Unlearning in Federated Learning (FL) presents significant challenges, as models grow and evolve with complex inheritance relationships. This complexity is amplified when blockchai…
TBDD: A New Trust-based, DRL-driven Framework for Blockchain Sharding in IoT
Zixu Zhang, Guangsheng Yu, Caijun Sun +7
Integrating sharded blockchain with IoT presents a solution for trust issues and optimized data flow. Sharding boosts blockchain scalability by dividing its nodes into parallel sha…
Split Unlearning
Guangsheng Yu, Yanna Jiang, Qin Wang +5
We introduce Split Unlearning, a novel machine unlearning technology designed for Split Learning (SL), enabling the first-ever implementation of Sharded, Isolated, Sliced, and Aggr…
A Secure Aggregation for Federated Learning on Long-Tailed Data
Yanna Jiang, Baihe Ma, Xu Wang +4
As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. I…
Blockchained Federated Learning for Internet of Things: A Comprehensive Survey
Yanna Jiang, Baihe Ma, Xu Wang +5
The demand for intelligent industries and smart services based on big data is rising rapidly with the increasing digitization and intelligence of the modern world. This survey comp…
Location Privacy Threats and Protections in 6G Vehicular Networks: A Comprehensive Review
Baihe Ma, Xu Wang, Xiaojie Lin +8
Location privacy is critical in vehicular networks, where drivers' trajectories and personal information can be exposed, allowing adversaries to launch data and physical attacks th…
IronForge: An Open, Secure, Fair, Decentralized Federated Learning
Guangsheng Yu, Xu Wang, Caijun Sun +5
Federated learning (FL) provides an effective machine learning (ML) architecture to protect data privacy in a distributed manner. However, the inevitable network asynchrony, the ov…
Towards Web3 Applications: Easing the Access and Transition
Guangsheng Yu, Xu Wang, Qin Wang +5
Web3 is leading a wave of the next generation of web services that even many Web2 applications are keen to ride. However, the lack of Web3 background for Web2 developers hinders ea…
Cross-chain between a Parent Chain and Multiple Side Chains
Guangsheng Yu, Xu Wang, Ren Ping Liu
In certain Blockchain systems, multiple Blockchains are required to operate cooperatively for security, performance, and capacity considerations. This invention defines a cross-cha…
Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning
Guangsheng Yu, Xu Wang, Ping Yu +3
Obfuscating a dataset by adding random noises to protect the privacy of sensitive samples in the training dataset is crucial to prevent data leakage to untrusted parties for edge a…
Capacity Analysis of Public Blockchain
Xu Wang, Wei Ni, Xuan Zha +4
As distributed ledgers, blockchains run consensus protocols which trade capacity for consistency, especially in non-ideal networks with incomplete connectivity and erroneous links.…