12 papers
Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
Ziqi Zhao, Jialin Lu, Junjie Shan +3
Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withho…
Confundo: Learning to Generate Robust Poison for Practical RAG Systems
Haoyang Hu, Zhejun Jiang, Yueming Lyu +3
Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear trustworthy. This trust has spurr…
DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
Qintong Zhang, Junyuan Zhang, Zhifei Ren +8
Document parsing aims to transform unstructured PDF images into semi-structured data, facilitating the digitization and utilization of information in diverse domains. While vision…
TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition
Junyuan Zhang, Bin Wang, Qintong Zhang +13
Table recognition (TR) aims to transform table images into semi-structured representations such as HTML or Markdown. As a core component of document parsing, TR has long relied on…
Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
Ziling Wang, Shuya Yang, Jialin Lu +1
Face recognition (FR) technologies are increasingly used to power large-scale image retrieval systems, raising serious privacy concerns. Services like Clearview AI and PimEyes allo…
Deep-Learning-Assisted Highly-Accurate COVID-19 Diagnosis on Lung Computed Tomography Images
Yinuo Wang, Juhyun Bae, Ka Ho Chow +2
COVID-19 is a severe and acute viral disease that can cause symptoms consistent with pneumonia in which inflammation is caused in the alveolous regions of the lungs leading to a bu…
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
Jialin Lu, Junjie Shan, Ziqi Zhao +1
As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by…
GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning
Rui Zhang, Ka-Ho Chow
The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL). In FL, clients jo…
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
Junyuan Zhang, Qintong Zhang, Bin Wang +6
Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without…
Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning
Junjie Shan, Ziqi Zhao, Jialin Lu +3
Foundation models that bridge vision and language have made significant progress. While they have inspired many life-enriching applications, their potential for abuse in creating n…
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
Jialin Lu, Junjie Shan, Ziqi Zhao +1
As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by…
Harmless Backdoor-based Client-side Watermarking in Federated Learning
Kaijing Luo, Ka-Ho Chow
Protecting intellectual property (IP) in federated learning (FL) is increasingly important as clients contribute proprietary data to collaboratively train models. Model watermarkin…