相关论文: Initial Exploration of Zero-Shot Privacy Utility T…

LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic fairness properties in this context are poorly understood. In this short technical report, we audit the algorithmic…

Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a…

Organizations that collect and analyze data may wish or be mandated by regulation to justify and explain their analysis results. At the same time, the logic that they have followed to analyze the data, i.e., their queries, may be…

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged for adapting LLMs to tabular data generation: (i) fine-tuning…

The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are…

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely…

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm…

We study privacy-utility trade-offs where users share privacy-correlated useful information with a service provider to obtain some utility. The service provider is adversarial in the sense that it can infer the users' private information…

Privacy-preserving machine learning (ML) seeks to balance data utility and privacy, especially as regulations like the GDPR mandate the anonymization of personal data for ML applications. Conventional anonymization approaches often reduce…

Anonymization techniques based on obfuscating the quasi-identifiers by means of value generalization hierarchies are widely used to achieve preset levels of privacy. To prevent different types of attacks against database privacy it is…

With the rapid adoption of Federated Learning (FL) as the training and tuning protocol for applications utilizing Large Language Models (LLMs), recent research highlights the need for significant modifications to FL to accommodate the…

We study (differentially) private federated learning (FL) of language models. The language models in cross-device FL are relatively small, which can be trained with meaningful formal user-level differential privacy (DP) guarantees when…

Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle…

As Large Language Models (LLMs) achieve remarkable success across a wide range of applications, such as chatbots and code copilots, concerns surrounding the generation of harmful content have come increasingly into focus. Despite…

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential…

While specialized learning-based models have historically dominated image privacy prediction, the current literature increasingly favours adopting large Vision-Language Models (VLMs) designed for generic tasks. This trend risks overlooking…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

Large Language Models (LLMs) have been extensively researched and used in both academia and industry since the rise in popularity of the Transformer model, which demonstrates excellent performance in AI. However, the computational demands…

Network data needs to be shared for distributed security analysis. Anonymization of network data for sharing sets up a fundamental tradeoff between privacy protection versus security analysis capability. This privacy/analysis tradeoff has…