Related papers: Impala: Low-Latency, Communication-Efficient Priva…

The longstanding goals of federated learning (FL) require rigorous privacy guarantees and low communication overhead while holding a relatively high model accuracy. However, simultaneously achieving all the goals is extremely challenging.…

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…

Hardware specialization is becoming a key enabler of energyefficient performance. Future systems will be increasingly heterogeneous, integrating multiple specialized and programmable accelerators, each with different memory demands.…

Personalized recommendation is an important class of deep-learning applications that powers a large collection of internet services and consumes a considerable amount of datacenter resources. As the scale of production-grade recommendation…

In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks with only a small set of examples at inference time, thereby avoiding task-specific fine-tuning. However, in-context examples may contain privacy-sensitive…

Effective communication is an essential component in collaborative multi-agent systems. Situations where explicit messaging is not feasible have been common in human society throughout history, which motivate the study of implicit…

We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records. By using differential privacy during training and homomorphic encryption during inference, we…

Large language model (LLM) based services are primarily structured as client-server interactions, with clients sending queries directly to cloud providers that host LLMs. This approach currently compromises data privacy as all queries must…

We propose a learning algorithm to design a light-weight neural multiplexer that given the input and computational resource requirements, calls the model that will consume the minimum compute resources for a successful inference. Mobile…

Federated learning (FL) has rapidly become a compelling paradigm that enables multiple clients to jointly train a model by sharing only gradient updates for aggregation, without revealing their local private data. In order to protect the…

With the increasing popularity of the cloud, clients oursource their data to clouds in order to take advantage of unlimited virtualized storage space and the low management cost. Such trend prompts the privately oursourcing computation,…

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value states into a low-rank latent vector, caching only this vector to reduce memory. In tensor parallelism (TP), however, attention heads are computed across…

Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted through continuous prompt learning. While discrete prompt optimization improves…

Hybrid private inference (PI) protocol, which synergistically utilizes both multi-party computation (MPC) and homomorphic encryption, is one of the most prominent techniques for PI. However, even the state-of-the-art PI protocols are…

We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training algorithm tailored to encrypted computation. Our approach…

Incorporating fully homomorphic encryption (FHE) into the inference process of a convolutional neural network (CNN) draws enormous attention as a viable approach for achieving private inference (PI). FHE allows delegating the entire…

Advanced computer vision technology can provide near real-time home monitoring to support "aging in place" by detecting falls and symptoms related to seizures and stroke. Affordable webcams, together with cloud computing services (to run…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

The widespread adoption of cloud-based solutions introduces privacy and security concerns. Techniques such as homomorphic encryption (HE) mitigate this problem by allowing computation over encrypted data without the need for decryption.…

The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a…