Related papers: TruncFormer: Private LLM Inference Using Only Trun…

Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…

Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world settings, these logs are often distributed across multiple organizations and cannot be…

Prominent Large Language Model (LLM) services from providers like OpenAI and Google excel at general tasks but often underperform on domain-specific applications. Current customization services for these LLMs typically require users to…

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However,…

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent to retraining, it is…

Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck,…

Large Language Models (LLMs) are increasingly being used for automated evaluations and explaining them. However, concerns about explanation quality, consistency, and hallucinations remain open research challenges, particularly in…

Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

As machine learning (ML) becomes more prevalent in human-centric applications, there is a growing emphasis on algorithmic fairness and privacy protection. While previous research has explored these areas as separate objectives, there is a…

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional…

At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are…

Large Language Models (LLMs) are emerging as powerful enablers for autonomous reasoning and natural-language coordination in unmanned aerial vehicle (UAV) swarms operating within Internet of Things (IoT) environments. However, existing…

The de-identification of private information in medical data is a crucial process to mitigate the risk of confidentiality breaches, particularly when patient personal details are not adequately removed before the release of medical records.…

Large language models (LLMs) are increasingly integrated into users' daily lives, leading to a growing demand for personalized outputs. Previous work focuses on leveraging a user's own history, overlooking inter-user differences that are…

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

Differential Privacy (DP) provides a rigorous framework for releasing statistics while protecting individual information present in a dataset. Although substantial progress has been made on differentially private linear regression, existing…