Related papers: Privacy-Preserving In-Context Learning with Differ…

Access to diverse, high-quality datasets is crucial for machine learning model performance, yet data sharing remains limited by privacy concerns and competitive interests, particularly in regulated domains like healthcare. This dynamic…

Local differential privacy (LDP) can provide each user with strong privacy guarantees under untrusted data curators while ensuring accurate statistics derived from privatized data. Due to its powerfulness, LDP has been widely adopted to…

Differential privacy is a leading protection setting, focused by design on individual privacy. Many applications, in medical / pharmaceutical domains or social networks, rather posit privacy at a group level, a setting we call integral…

As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the…

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

This paper proposes a personalization method for speech emotion recognition (SER) through in-context learning (ICL). Since the expression of emotions varies from person to person, speaker-specific adaptation is crucial for improving the SER…

State-of-the-art large language models (LLMs) are typically deployed as online services, requiring users to transmit detailed prompts to cloud servers. This raises significant privacy concerns. In response, we introduce ConfusionPrompt, a…

Quantum computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…

For systems whose states implicate sensitive information, their privacy is of great concern. While notions like differential privacy have been successfully introduced to dynamical systems, it is still unclear how a system's privacy can be…

With approximately 7,000 languages spoken worldwide, current large language models (LLMs) support only a small subset. Prior research indicates LLMs can learn new languages for certain tasks without supervised data. We extend this…

In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language…

In-context learning (ICL) allows LLMs to adapt to new tasks via a few demonstrations, but those demonstrations may contain sensitive data. Differentially private (DP) ICL mechanisms mitigate this risk by injecting noise into the aggregation…

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as ICL demonstrations increase from a few to many, performance tends to plateau and eventually decline. We identify two…

Large Language Models (LLMs) demonstrate proficiency across diverse tasks but often require targeted adaptations for specific applications. Various methods have been proposed to facilitate this adaptation, including fewshot fine-tuning,…

In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…

Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical evaluations on these models, there has been a gap in providing…

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vision, speech recognition, object detection, to name a few. The principal reason for this success is the availability of huge datasets for…

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…