Related papers: PrivacyScalpel: Enhancing LLM Privacy via Interpre…

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

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…

Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its Right to be…

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognize and appropriately handle privacy-sensitive content is essential. We conduct a comprehensive evaluation of ten…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heterogeneous, locale-dependent, context-sensitive, and often…

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that…

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…

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples contributed by each user. We study two variants of DP-SGD…

This article explores the gaps that can manifest when using a large language model (LLM) to obtain simplified interpretations of data practices from a complex privacy policy. We exemplify these gaps to showcase issues in accuracy,…

As large language models (LLMs) increasingly underpin technological advancements, the privacy of their training data emerges as a critical concern. Differential Privacy (DP) serves as a rigorous mechanism to protect this data, yet its…

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective…

Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy risk. To mitigate the privacy concerns of LMs, machine…

Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need…

Web-based Large Language Model (LLM) services have been widely adopted and have become an integral part of our Internet experience. Third-party plugins enhance the functionalities of LLM by enabling access to real-world data and services.…

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

Removing Personally Identifiable Information (PII) from clinical notes in Electronic Health Records (EHRs) is essential for research and AI development. While Large Language Models (LLMs) are powerful, their high computational costs and the…