Publications (28)
A New Dataset and Comparative Study for Aphid Cluster Detection
Tianxiao Zhang, Kaidong Li, Xiangyu Chen +7
Aphids are one of the main threats to crops, rural families, and global food security. Chemical pest control is a necessary component of crop production for maximizing yields, howe…
Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models
Tianxiao Zhang, Kaidong Li, Xiangyu Chen +7
Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying…
Cyber-Physical Systems Security -- A Survey
Abdulmalik Humayed, Jingqiang Lin, Fengjun Li +1
With the exponential growth of cyber-physical systems (CPS), new security challenges have emerged. Various vulnerabilities, threats, attacks, and controls have been introduced for…
Gender, Smoking History and Age Prediction from Laryngeal Images
Tianxiao Zhang, Andrés M. Bur, Shannon Kraft +5
Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced…
Counterfactual Prediction Under Selective Confounding
Sohaib Kiani, Jared Barton, Jon Sushinsky +2
This research addresses the challenge of conducting interpretable causal inference between a binary treatment and its resulting outcome when not all confounders are known. Confound…
Improving Vision Transformers by Overlapping Heads in Multi-Head Self-Attention
Tianxiao Zhang, Bo Luo, Guanghui Wang
Vision Transformers have made remarkable progress in recent years, achieving state-of-the-art performance in most vision tasks. A key component of this success is due to the introd…
The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
Yuying Li, Zeyan Liu, Junyi Zhao +4
Generative AI models can produce high-quality images based on text prompts. The generated images often appear indistinguishable from images generated by conventional optical photog…
Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs
Tianxiao Zhang, Bo Luo, Ajay Sharda +1
Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. F…
PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing
Liangqin Ren, Zeyan Liu, Ye Wang +3
Deepfakes, especially face-swapping attacks, pose significant challenges to authenticity, security, and ethics across science, engineering, and society. While most existing detecti…
The Power of Bamboo: On the Post-Compromise Security for Searchable Symmetric Encryption
Tianyang Chen, Peng Xu, Stjepan Picek +4
Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without los…
d-DSE: Distinct Dynamic Searchable Encryption Resisting Volume Leakage in Encrypted Databases
Dongli Liu, Wei Wang, Peng Xu +3
Dynamic Searchable Encryption (DSE) has emerged as a solution to efficiently handle and protect large-scale data storage in encrypted databases (EDBs). Volume leakage poses a signi…
Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
Bo Luo, Yannan Liu, Lingxiao Wei +1
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applicat…
Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency
Sohaib Kiani, Sana Awan, Chao Lan +2
In the evasion attacks against deep neural networks (DNN), the attacker generates adversarial instances that are visually indistinguishable from benign samples and sends them to th…
On Functional Test Generation for Deep Neural Network IPs
Bo Luo, Yu Li, Lingxiao Wei +1
Machine learning systems based on deep neural networks (DNNs) produce state-of-the-art results in many applications. Considering the large amount of training data and know-how requ…
PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption
Liangqin Ren, Zeyan Liu, Fengjun Li +3
In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (…
On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
Zeyan Liu, Zijun Yao, Fengjun Li +1
With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim…
Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples
Bo Luo, Qiang Xu
Deep neural networks (DNNs) are shown to be susceptible to adversarial example attacks. Most existing works achieve this malicious objective by crafting subtle pixel-wise perturbat…
On Configurable Defense against Adversarial Example Attacks
Bo Luo, Min Li, Yu Li +1
Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications. Recently, however, DNNs are shown to be vulnerable to adversaria…
I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
Lingxiao Wei, Bo Luo, Yu Li +2
Deep learning has become the de-facto computational paradigm for various kinds of perception problems, including many privacy-sensitive applications such as online medical image an…
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
Tianxiao Zhang, Wenju Xu, Bo Luo +1
The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various comp…
Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems
Zeyan Liu, Fengjun Li, Jingqiang Lin +2
With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the…
CSRN: Collaborative Sequential Recommendation Networks for News Retrieval
Bing Bai, Guanhua Zhang, Ye Lin +3
Nowadays, news apps have taken over the popularity of paper-based media, providing a great opportunity for personalization. Recurrent Neural Network (RNN)-based sequential recommen…
Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction
Tao Zhe, Haoyu Wang, Bo Luo +6
Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Ex…
Learning Social Circles in Ego Networks based on Multi-View Social Graphs
Chao Lan, Yuhao Yang, Xiaoli Li +2
In social network analysis, automatic social circle detection in ego-networks is becoming a fundamental and important task, with many potential applications such as user privacy pr…
DeepDyve: Dynamic Verification for Deep Neural Networks
Yu Li, Min Li, Bo Luo +2
Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, how…
Accurate and Scalable Multimodal Pathology Retrieval via Attentive Vision-Language Alignment
Hongyi Wang, Zhengjie Zhu, Jiabo Ma +9
The rapid digitization of histopathology slides has opened up new possibilities for computational tools in clinical and research workflows. Among these, content-based slide retriev…
Semantic Clustering based Deduction Learning for Image Recognition and Classification
Wenchi Ma, Xuemin Tu, Bo Luo +1
The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains. Human beings can make judgments based on experienc…
Resource-Interaction Graph: Efficient Graph Representation for Anomaly Detection
James Pope, Jinyuan Liang, Vijay Kumar +13
Security research has concentrated on converting operating system audit logs into suitable graphs, such as provenance graphs, for analysis. However, provenance graphs can grow very…