Related papers: Data-adaptive Differentially Private Prompt Synthe…

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…

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data…

Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The…

Large Language Models (LLMs) are powerful tools for natural language processing, enabling novel applications and user experiences. However, to achieve optimal performance, LLMs often require adaptation with private data, which poses privacy…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

SpeechLLMs are increasingly deployed in professional settings where domain customisation is standard practice: users supply context in prompts with sensitive information, fine-tune on proprietary recordings, or both. We identify and…

Differential Privacy (DP) is a widely adopted technique, valued for its effectiveness in protecting the privacy of task-specific datasets, making it a critical tool for large language models. However, its effectiveness in Multimodal Large…

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student…

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of designing distributed…

Decentralized Federated Learning (DFL) enables collaborative model training without a central server, but it remains vulnerable to privacy leakage because shared model updates can expose sensitive information through inversion,…

Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information (PII), which could be exposed to third parties hosting these…

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

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…

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…

Reinforcement learning (RL) presents numerous benefits compared to rule-based approaches in various applications. Privacy concerns have grown with the widespread use of RL trained with privacy-sensitive data in IoT devices, especially for…

Pre-trained Language Models (PLMs) have demonstrated impressive performance in various NLP tasks. However, traditional fine-tuning methods for leveraging PLMs for downstream tasks entail significant computational overhead. Prompt-tuning has…

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability…

Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL…

We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy. Our algorithm makes adaptive use of a continuous relaxation of…