Related papers: Trustworthy and Controllable Professional Knowledg…

Trusted Execution Environments (TEEs) protect sensitive code and data from the operating system, hypervisor, or other untrusted software. Different solutions exist, each proposing different features. Abstraction layers aim to unify the…

The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a…

Trusted Execution Environments (TEEs) are a feature of modern central processing units (CPUs) that aim to provide a high assurance, isolated environment in which to run workloads that demand both confidentiality and integrity. Hardware and…

Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work, we…

Limited by the scale and diversity of time series data, the neural networks trained on time series data often overfit and show unsatisfacotry performances. In comparison, large language models (LLMs) recently exhibit impressive…

Cloud workloads have dominated generative AI based on large language models (LLM). Specialized hardware accelerators, such as GPUs, NPUs, and TPUs, play a key role in AI adoption due to their superior performance over general-purpose CPUs.…

Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose…

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. However, their performance may be suboptimal for domain-specific tasks that…

The capabilities of Large Language Models (LLMs) have opened new frontiers for interacting with complex, domain-specific knowledge. However, prevailing methods like Retrieval-Augmented Generation (RAG) and general-purpose Agentic AI, while…

This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high…

Large Language Models (LLMs) often struggle to align their responses with objective facts, resulting in the issue of factual hallucinations, which can be difficult to detect and mislead users without relevant knowledge. Although…

Privacy and security challenges in Machine Learning (ML) have become increasingly severe, along with ML's pervasive development and the recent demonstration of large attack surfaces. As a mature system-oriented approach, Confidential…

CPU-based trusted execution environments (TEEs) and differential privacy (DP) have gained wide applications for private inference. Due to high inference latency in TEEs, researchers use partition-based approaches that offload linear model…

Despite the impressive performance of large language models (LLMs) pretrained on vast knowledge corpora, advancing their knowledge manipulation-the ability to effectively recall, reason, and transfer relevant knowledge-remains challenging.…

Deriving operational intelligence from organizational data repositories is a key challenge due to the dichotomy of data confidentiality vs data integration objectives, as well as the limitations of Natural Language Processing (NLP) tools…

Traditional Business Process Management (BPM) struggles with rigidity, opacity, and scalability in dynamic environments while emerging Large Language Models (LLMs) present transformative opportunities alongside risks. This paper explores…

Previous studies have revealed that vanilla pre-trained language models (PLMs) lack the capacity to handle knowledge-intensive NLP tasks alone; thus, several works have attempted to integrate external knowledge into PLMs. However, despite…

Scientific computing sometimes involves computation on sensitive data. Depending on the data and the execution environment, the HPC (high-performance computing) user or data provider may require confidentiality and/or integrity guarantees.…

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

Serving Large Language Models (LLMs) is critical for AI-powered applications, yet it demands substantial computational resources, particularly in memory bandwidth and computational throughput. Low-precision computation has emerged as a key…