569 citations · 863 across the 18 of their papers we have counts for
20 papers
When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers
Zhaoxin Zhang, Borui Chen, Yiming Hu +3
Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts…
Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
Chenchen Tan, Youyang Qu, Xinghao Li +4
The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential reten…
Causal Fingerprints of AI Generative Models
Hui Xu, Chi Liu, Congcong Zhu +3
AI generative models leave implicit traces in their generated images, which are commonly referred to as model fingerprints and are exploited for source attribution. Prior methods r…
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey
Yichen Wan, Youyang Qu, Wei Ni +3
Due to the greatly improved capabilities of devices, massive data, and increasing concern about data privacy, Federated Learning (FL) has been increasingly considered for applicati…
Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System
Jiwei Guan, Lei Pan, Chen Wang +3
There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become avai…
Hybrid Variational Autoencoder for Time Series Forecasting
Borui Cai, Shuiqiao Yang, Longxiang Gao +1
Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly lea…
From Wide to Deep: Dimension Lifting Network for Parameter-efficient Knowledge Graph Embedding
Borui Cai, Yong Xiang, Longxiang Gao +4
Knowledge graph embedding (KGE) that maps entities and relations into vector representations is essential for downstream applications. Conventional KGE methods require high-dimensi…
An Optimized Privacy-Utility Trade-off Framework for Differentially Private Data Sharing in Blockchain-based Internet of Things
Muhammad Islam, Mubashir Husain Rehmani, Jinjun Chen
Differential private (DP) query and response mechanisms have been widely adopted in various applications based on Internet of Things (IoT) to leverage variety of benefits through d…
A Comprehensive Survey on Edge Data Integrity Verification: Fundamentals and Future Trends
Yao Zhao, Youyang Qu, Yong Xiang +3
Recent advances in edge computing~(EC) have pushed cloud-based data caching services to edge, however, such emerging edge storage comes with numerous challenging and unique securit…
An Efficient and Reliable Asynchronous Federated Learning Scheme for Smart Public Transportation
Chenhao Xu, Youyang Qu, Tom H. Luan +3
Since the traffic conditions change over time, machine learning models that predict traffic flows must be updated continuously and efficiently in smart public transportation. Feder…
Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting
Qi Zhong, Leo Yu Zhang, Shengshan Hu +3
Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models. However, when the source data is unavailable, it is challenging to just erase the wat…
Blockchain-based Digital Twin for Supply Chain Management: State-of-the-Art Review and Future Research Directions
Jiongbin Liu, William Yeoh, Youyang Qu +1
Supply chain management (SCM) plays a vital role in the global economy, as evidenced by recent COVID-19 supply chain challenges. Traditional SCM faces security and efficiency issue…
Temporal Knowledge Graph Completion: A Survey
Borui Cai, Yong Xiang, Longxiang Gao +3
Knowledge graph completion (KGC) can predict missing links and is crucial for real-world knowledge graphs, which widely suffer from incompleteness. KGC methods assume a knowledge g…
Semantic Code Search for Smart Contracts
Chaochen Shi, Yong Xiang, Jiangshan Yu +1
Semantic code search technology allows searching for existing code snippets through natural language, which can greatly improve programming efficiency. Smart contracts, programs th…
Asynchronous Federated Learning on Heterogeneous Devices: A Survey
Chenhao Xu, Youyang Qu, Yong Xiang +1
Federated learning (FL) is a kind of distributed machine learning framework, where the global model is generated on the centralized aggregation server based on the parameters of lo…
Low-level Comments auto-generation for Solidity Smart Contracts
Chaochen Shi, Yong Xiang, Jiangshan Yu +2
Context: Decentralized applications on blockchain platforms are realized through smart contracts. However, participants who lack programming knowledge often have difficulties readi…
A Bytecode-based Approach for Smart Contract Classification
Chaochen Shi, Yong Xiang, Robin Ram Mohan Doss +3
With the development of blockchain technologies, the number of smart contracts deployed on blockchain platforms is growing exponentially, which makes it difficult for users to find…
SCEI: A Smart-Contract Driven Edge Intelligence Framework for IoT Systems
Chenhao Xu, Jiaqi Ge, Yong Li +5
Federated learning (FL) enables collaborative training of a shared model on edge devices while maintaining data privacy. FL is effective when dealing with independent and identical…
Chaotic-to-Fine Clustering for Unlabeled Plant Disease Images
Uno Fang, Jianxin Li, Xuequan Lu +3
Current annotation for plant disease images depends on manual sorting and handcrafted features by agricultural experts, which is time-consuming and labour-intensive. In this paper,…
Fog Computing: Survey of Trends, Architectures, Requirements, and Research Directions
Ranesh Kumar Naha, Saurabh Garg, Dimitrios Georgakopoulos +4
Emerging technologies like the Internet of Things (IoT) require latency-aware computation for real-time application processing. In IoT environments, connected things generate a hug…