Related papers: ACTG-ARL: Differentially Private Conditional Text …

Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance…

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tuning or resort to extra attribute classifiers, yet suffer…

Prompt learning with immensely large Casual Language Models (CLMs) has been shown promising for attribute-controllable text generation (CTG). However, vanilla prompt tuning tends to imitate training corpus characteristics beyond the control…

Programmatically generated synthetic data has been used in differential private training for classification to enhance performance without privacy leakage. However, as the synthetic data is generated from a random process, the distribution…

We introduce a new class of range restricted formal data privacy standards that condition on owner beliefs about sensitive data ranges. By incorporating this additional information, we can provide a stronger privacy guarantee (e.g. an…

Multimodal Retrieval-Augmented Generation (MRAG) systems enhance LMMs by integrating external multimodal databases, but introduce unexplored privacy vulnerabilities. While text-based RAG privacy risks have been studied, multimodal data…

Large ASR models can inadvertently leak sensitive information, which can be mitigated by formal privacy measures like differential privacy (DP). However, traditional DP training is computationally expensive, and can hurt model performance.…

Deep reinforcement learning has demonstrated remarkable success across various domains. However, the tight coupling between training and inference processes makes accelerating DRL training an essential challenge for DRL optimization. Two…

Large-scale data collection, from national censuses to IoT-enabled smart homes, routinely gathers dozens of attributes per individual. These multi-attribute datasets are crucial for analytics but pose significant privacy risks. Local…

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However,…

Controller synthesis is a formal method approach for automatically generating Labeled Transition System (LTS) controllers that satisfy specified properties. The efficiency of the synthesis process, however, is critically dependent on…

We propose ARISE, a framework that iteratively induces rules and generates synthetic data for text classification. We combine synthetic data generation and automatic rule induction, via bootstrapping, to iteratively filter the generated…

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full…

Incremental learning is one paradigm to enable model building and updating at scale with streaming data. For end-to-end automatic speech recognition (ASR) tasks, the absence of human annotated labels along with the need for privacy…

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…

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in…

Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a method for generating…

Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some unique challenges such as capturing dependencies in…

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel…

Data is the lifeblood of the modern world, forming a fundamental part of AI, decision-making, and research advances. With increase in interest in data, governments have taken important steps towards a regulated data world, drastically…