Related papers: DSperse: A Framework for Targeted Verification in …

Over the last years, security kernels have played a promising role in reshaping the landscape of platform security on today's ubiquitous embedded devices. Security kernels, such as separation kernels, enable constructing high-assurance…

When training a machine learning model, it is standard procedure for the researcher to have full knowledge of both the data and model. However, this engenders a lack of trust between data owners and data scientists. Data owners are…

Extreme multi-label classification refers to supervised multi-label learning involving hundreds of thousands or even millions of labels. Datasets in extreme classification exhibit fit to power-law distribution, i.e. a large fraction of…

Machine learning is promising, but it often needs to process vast amounts of sensitive data which raises concerns about privacy. In this white-paper, we introduce Substra, a distributed framework for privacy-preserving, traceable and…

Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a signal. As a result, they erase sparsity patterns and perform…

Data privacy concerns often prevent the use of cloud-based machine learning services for sensitive personal data. While homomorphic encryption (HE) offers a potential solution by enabling computations on encrypted data, the challenge is to…

Across industries, there is an ever-increasing rate of data sharing for collaboration and innovation between organizations and their customers, partners, suppliers, and internal teams. However, many enterprises are restricted from freely…

Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rule-based models offer global and exact interpretability, learning rule sets that…

In recent years, DeepSeek has achieved strong inference performance but remains hard to deploy on energy-constrained edge devices. This paper presents the DeepSeek Processing Element (DSPE), an edge-oriented architecture that alleviates the…

This letter proposes a sparse diffusion steepest-descent algorithm for one bit compressed sensing in wireless sensor networks. The approach exploits the diffusion strategy from distributed learning in the one bit compressed sensing…

In the last decade, data-driven algorithms outperformed traditional optimization-based algorithms in many research areas, such as computer vision, natural language processing, etc. However, extensive data usages bring a new challenge or…

Collaborative inference has received significant research interest in machine learning as a vehicle for distributing computation load, reducing latency, as well as addressing privacy preservation in communications. Recent collaborative…

As inference scales to multi-node deployments, disaggregation - splitting inference into distinct phases - offers a promising path to improving the throughput-interactivity Pareto frontier. Despite growing enthusiasm and a surge of…

Machine learning applications are increasingly deployed not only to serve predictions using static models, but also as tightly-integrated components of feedback loops involving dynamic, real-time decision making. These applications pose a…

Distributed optimization has been widely used as one of the most efficient approaches for model training with massive samples. However, large-scale learning problems with both massive samples and high-dimensional features widely exist in…

Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due…

Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…

Zero-knowledge proofs allow verification of computations without revealing private information. However, existing systems require memory proportional to the computation size, which has historically limited use in large-scale applications…

Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches proposed so far achieve these guarantees but severely reduce model accuracy. We propose sequential…

Verifiable Secret-Sharing (VSS) is a fundamental primitive in secure distributed computing. It is used as a building block in several distributed computing tasks, such as Byzantine agreement and secure multi-party computation. In this…