Ying He

Baihe Ma, Yanna Jiang, Xu Wang et al.

As Large Language Models (LLMs) are increasingly deployed in sensitive domains, traditional data privacy measures prove inadequate for protecting information that is implicit, contextual, or inferable - what we define as semantic privacy. This Systematization of Knowledge (SoK) introduces a lifecycle-centric framework to analyze how semantic privacy risks emerge across input processing, pretraining, fine-tuning, and alignment stages of LLMs. We categorize key attack vectors and assess how current defenses, such as differential privacy, embedding encryption, edge computing, and unlearning, address these threats. Our analysis reveals critical gaps in semantic-level protection, especially against contextual inference and latent representation leakage. We conclude by outlining open challenges, including quantifying semantic leakage, protecting multimodal inputs, balancing de-identification with generation quality, and ensuring transparency in privacy enforcement. This work aims to inform future research on designing robust, semantically aware privacy-preserving techniques for LLMs.

Junhui Hou, Lap-Pui Chau, Nadia Magnenat-Thalmann et al.

Low-rank matrix approximation (LRMA) is a powerful technique for signal processing and pattern analysis. However, its potential for data compression has not yet been fully investigated in the literature. In this paper, we propose sparse low-rank matrix approximation (SLRMA), an effective computational tool for data compression. SLRMA extends the conventional LRMA by exploring both the intra- and inter-coherence of data samples simultaneously. With the aid of prescribed orthogonal transforms (e.g., discrete cosine/wavelet transform and graph transform), SLRMA decomposes a matrix into a product of two smaller matrices, where one matrix is made of extremely sparse and orthogonal column vectors, and the other consists of the transform coefficients. Technically, we formulate SLRMA as a constrained optimization problem, i.e., minimizing the approximation error in the least-squares sense regularized by $\ell_0$-norm and orthogonality, and solve it using the inexact augmented Lagrangian multiplier method. Through extensive tests on real-world data, such as 2D image sets and 3D dynamic meshes, we observe that (i) SLRMA empirically converges well; (ii) SLRMA can produce approximation error comparable to LRMA but in a much sparse form; (iii) SLRMA-based compression schemes significantly outperform the state-of-the-art in terms of rate-distortion performance.