Related papers: Privacy-Preserving Screening for Record Linkage
Correspondence-based point cloud registration (PCR) plays a key role in robotics and computer vision. However, challenges like sensor noises, object occlusions, and descriptor limitations inevitably result in numerous outliers. RANSAC…
Partial Least Squares (PLS) methods have been heavily exploited to analyse the association between two blocs of data. These powerful approaches can be applied to data sets where the number of variables is greater than the number of…
The use of Deep Learning in the medical field is hindered by the lack of interpretability. Case-based interpretability strategies can provide intuitive explanations for deep learning models' decisions, thus, enhancing trust. However, the…
Recent advancements in large language models (LLMs) integrating explicit reasoning, such as OpenAI's o3-mini, DeepSeek-R1, and QWQ-32B, enable smaller models to solve complex tasks by generating intermediate reasoning steps prior to…
Fine-tuning large vision models (LVMs) and large language models (LLMs) under differentially private federated learning (DPFL) is hindered by a fundamental privacy-utility trade-off. Low-Rank Adaptation (LoRA), a promising…
Recently collaborative learning is widely applied to model sensitive data generated in Industrial IoT (IIoT). It enables a large number of devices to collectively train a global model by collaborating with a server while keeping the…
Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…
With the rapid increase in computing, storage and networking resources, data is not only collected and stored, but also analyzed. This creates a serious privacy problem which often inhibits the use of this data. In this chapter, we…
Deep learning (DL) has demonstrated significant potential across various safety-critical applications, yet ensuring its robustness remains a key challenge. While adversarial robustness has been extensively studied in worst-case scenarios,…
Privacy-preserving machine learning (PPML) enables clients to collaboratively train deep learning models without sharing private datasets, but faces privacy leakage risks due to gradient leakage attacks. Prevailing methods leverage secure…
Recommendation systems usually involve exploiting the relations among known features and content that describe items (content-based filtering) or the overlap of similar users who interacted with or rated the target item (collaborative…
The widespread deployment of high-resolution visual sensing systems, coupled with the rise of foundation models, has amplified privacy risks in video-based applications. Differentially private pixelization offers mathematically guaranteed…
In Near-Neighbor Search (NNS), a new client queries a database (held by a server) for the most similar data (near-neighbors) given a certain similarity metric. The Privacy-Preserving variant (PP-NNS) requires that neither server nor the…
Existing methods for rotation estimation between two spherical ($\mathbb{S}^2$) patterns typically rely on spherical cross-correlation maximization between two spherical function. However, these approaches exhibit computational complexities…
Loyalty programs in the form of punch cards that can be redeemed for benefits have long been a ubiquitous element of the consumer landscape. However, their increasingly popular digital equivalents, while providing more convenience and…
Channel state information (CSI) acquisition is essential for the base station (BS) to fully reap the beamforming gain in intelligent reflecting surface (IRS)-aided downlink communication systems. Recently, [1] revealed a strong correlation…
A major impediment to research on improving peer review is the unavailability of peer-review data, since any release of such data must grapple with the sensitivity of the peer review data in terms of protecting identities of reviewers from…
Despite achieving good performance and wide adoption, machine learning based security detection models (e.g., malware classifiers) are subject to concept drift and evasive evolution of attackers, which renders up-to-date threat data as a…
Software composition analysis (SCA) denotes the process of identifying open-source software components in an input software application. SCA has been extensively developed and adopted by academia and industry. However, we notice that the…
Deep neural network (DNN) inference based on secure 2-party computation (2PC) can offer cryptographically-secure privacy protection but suffers from orders of magnitude latency overhead due to enormous communication. Previous works heavily…