Related papers: Making Translators Privacy-aware on the User's Sid…
As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools,…
Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…
Large language model (LLM) services have been rapidly integrated into people's daily lives as chatbots and agentic systems. They are nourished by collecting rich streams of data, raising privacy concerns around excessive collection of…
Differential privacy (DP) has steadily become the de-facto standard for achieving privacy in data analysis, which is typically implemented either in the "central" or "local" model. The local model has been more popular for commercial…
We present STAMP (Selective Task-Aware Mechanism for Text Privacy), a new framework for task-aware text privatization that achieves an improved privacy-utility trade-off. STAMP selectively allocates privacy budgets across tokens by jointly…
While neural machine translation (NMT) has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in NMT models leads to…
With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior…
Process mining aims to provide insights into the actual processes based on event data. These data are often recorded by information systems and are widely available. However, they often contain sensitive private information that should be…
This research addresses the growing need for privacy-preserving and accessible language translation by developing a fully offline Neural Machine Translation (NMT) system for Vietnamese-English translation on iOS devices. Given increasing…
TLS is an end-to-end protocol designed to provide confidentiality and integrity guarantees that improve end-user security and privacy. While TLS helps defend against pervasive surveillance of intercepted unencrypted traffic, it also hinders…
While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…
Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…
Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…
Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…
The rise of end-user applications powered by large language models (LLMs), including both conversational interfaces and add-ons to existing graphical user interfaces (GUIs), introduces new privacy challenges. However, many users remain…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…
Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…
Gender bias in machine translation (MT) is recognized as an issue that can harm people and society. And yet, advancements in the field rarely involve people, the final MT users, or inform how they might be impacted by biased technologies.…
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…