With the widespread adoption of cloud computing, the need for outsourcing statistical analysis to third-party platforms is growing rapidly. However, handling sensitive data such as medical records and financial information in cloud environments raises serious privacy concerns. In this paper, we present PP-STAT, a novel and efficient Homomorphic Encryption (HE)-based framework for privacy-preserving statistical analysis. HE enables computations to be performed directly on encrypted data without revealing the underlying plaintext. PP-STAT supports advanced statistical measures, including Z-score normalization, skewness, kurtosis, coefficient of variation, and Pearson correlation coefficient, all computed securely over encrypted data. To improve efficiency, PP-STAT introduces two key optimizations: (1) a Chebyshev-based approximation strategy for initializing inverse square root operations, and (2) a pre-normalization scaling technique that reduces multiplicative depth by folding constant scaling factors into mean and variance computations. These techniques significantly lower computational overhead and minimize the number of expensive bootstrapping procedures. Our evaluation on real-world datasets demonstrates that PP-STAT achieves high numerical accuracy, with mean relative error (MRE) below 2.4x10-4. Notably, the encrypted Pearson correlation coefficient between the smoker attribute and charges reaches 0.7873, with an MRE of 2.86x10-4. These results confirm the practical utility of PP-STAT for secure and precise statistical analysis in privacy-sensitive domains.

Fingerprint authentication is a popular security mechanism for smartphones and laptops. However, its adoption in web and cloud environments has been limited due to privacy concerns over storing and processing biometric data on servers. This paper introduces Blind-Touch, a novel machine learning-based fingerprint authentication system leveraging homomorphic encryption to address these privacy concerns. Homomorphic encryption allows computations on encrypted data without decrypting. Thus, Blind-Touch can keep fingerprint data encrypted on the server while performing machine learning operations. Blind-Touch combines three strategies to efficiently utilize homomorphic encryption in machine learning: (1) It optimizes the feature vector for a distributed architecture, processing the first fully connected layer (FC-16) in plaintext on the client side and the subsequent layer (FC-1) post-encryption on the server, thereby minimizing encrypted computations; (2) It employs a homomorphic encryption-compatible data compression technique capable of handling 8,192 authentication results concurrently; and (3) It utilizes a clustered server architecture to simultaneously process authentication results, thereby enhancing scalability with increasing user numbers. Blind-Touch achieves high accuracy on two benchmark fingerprint datasets, with a 93.6% F1- score for the PolyU dataset and a 98.2% F1-score for the SOKOTO dataset. Moreover, Blind-Touch can match a fingerprint among 5,000 in about 0.65 seconds. With its privacy-focused design, high accuracy, and efficiency, Blind-Touch is a promising alternative to conventional fingerprint authentication for web and cloud applications.

Modern transformer-based Large Language Models (LLMs) are constructed with a series of decoder blocks. Each block comprises three key components: (1) QKV generation, (2) multi-head attention, and (3) feed-forward networks. In batched processing, QKV generation and feed-forward networks involve compute-intensive matrix-matrix multiplications (GEMM), while multi-head attention requires bandwidth-heavy matrix-vector multiplications (GEMV). Machine learning accelerators like TPUs or NPUs are proficient in handling GEMM but are less efficient for GEMV computations. Conversely, Processing-in-Memory (PIM) technology is tailored for efficient GEMV computation, while it lacks the computational power to handle GEMM effectively.

We present Blind-Match, a novel biometric identification system that leverages homomorphic encryption (HE) for efficient and privacy-preserving 1:N matching. Blind-Match introduces a HE-optimized cosine similarity computation method, where the key idea is to divide the feature vector into smaller parts for processing rather than computing the entire vector at once. By optimizing the number of these parts, Blind-Match minimizes execution time while ensuring data privacy through HE. Blind-Match achieves superior performance compared to state-of-the-art methods across various biometric datasets. On the LFW face dataset, Blind-Match attains a 99.63% Rank-1 accuracy with a 128-dimensional feature vector, demonstrating its robustness in face recognition tasks. For fingerprint identification, Blind-Match achieves a remarkable 99.55% Rank-1 accuracy on the PolyU dataset, even with a compact 16-dimensional feature vector, significantly outperforming the state-of-the-art method, Blind-Touch, which achieves only 59.17%. Furthermore, Blind-Match showcases practical efficiency in large-scale biometric identification scenarios, such as Naver Cloud's FaceSign, by processing 6,144 biometric samples in 0.74 seconds using a 128-dimensional feature vector.

This paper presents a real-time embedded thermal imaging system architecture for compact, energy-efficient, high-quality imaging utilizing heterogeneous system-on-chip (SoC) and uncooled infrared focal plane arrays (IRFPAs). Unlike previous systems that organized separate devices for complex image processing, our system provides integrated image processing support for robust sensor-to-surveillance. The image processing organizes two algorithm stacks: a non-uniformity correction stack to mitigate the distinctive noise vulnerabilities of uncooled IRFPAs, and an image enhancement stack including contrast enhancement and temporal noise filters. We optimized these algorithms for domain-specific factors, including asymmetric multiprocessing (AMP), cache organization, single instruction multiple data (SIMD) instructions, and very long instruction word (VLIW) architectures. The implementation on the TI TDA3x SoC demonstrates that our system can process 640×480, 60 frames per second (FPS) videos at a peak core load of 57.5% while consuming power less than 2.2 W for the entire system, denoting the possibility of processing the 1280×1024, 30 FPS videos from the cutting-edge uncooled IRFPAs. Additionally, our system improves power efficiency by 9.42% and 9.96% at 30 and 60 FPS, respectively, compared to the state-of-the-art when executing similar image processing algorithms.

This paper presents an integrated image processor architecture designed for realtime interfacing and processing of high-resolution thermal video obtained from an uncooled infrared focal plane array (IRFPA) utilizing a modern system-on-chip field-programmable gate array (SoC FPGA). Our processor provides a one-chip solution for incorporating non-uniformity correction (NUC) algorithms and contrast enhancement methods (CEM) to be performed seamlessly. We have employed NUC algorithms that utilize multiple coefficients to ensure robust image quality, free from ghosting effects and blurring. These algorithms include polynomial modeling-based thermal drift compensation (TDC), two-point correction (TPC), and runtime discrete flat field correction (FFC). To address the memory bottlenecks originating from the parallel execution of NUC algorithms in realtime, we designed accelerators and parallel caching modules for pixel-wise algorithms based on a multi-parameter polynomial expression. Furthermore, we designed a specialized accelerator architecture to minimize the interrupted time for runtime FFC. The implementation on the XC7Z020CLG400 SoC FPGA with the QuantumRed VR thermal module demonstrates that our image processing module achieves a throughput of 60 frames per second (FPS) when processing 14-bit 640×480 resolution infrared video acquired from an uncooled IRFPA.