相关论文: Tau-Eval: A Unified Evaluation Framework for Usefu…
The widespread exchange of digital documents in various domains has resulted in abundant private information being shared. This proliferation necessitates redaction techniques to protect sensitive content and user privacy. While numerous…
Releasing Web query logs which contain valuable information for research or marketing, can breach the privacy of search engine users. Therefore rendering query logs to limit linking a query to an individual while preserving the data…
Attribute inference - the process of analyzing publicly available data in order to uncover hidden information - has become a major threat to privacy, given the recent technological leap in machine learning. One way to tackle this threat is…
Large language models (LLMs) are increasingly used in sensitive domains, where their ability to infer personal data from seemingly benign text introduces emerging privacy risks. While recent LLM-based anonymization methods help mitigate…
The rapid development of video surveillance systems for object detection, tracking, activity recognition, and anomaly detection has revolutionized our day-to-day lives while setting alarms for privacy concerns. It isn't easy to strike a…
Ensuring privacy of sensitive data is essential in many contexts, such as healthcare data, banks, e-commerce, wireless sensor networks, and social networks. It is common that different entities coordinate or want to rely on a third party to…
There is a growing need to gain insight into language model capabilities that relate to sensitive topics, such as bioterrorism or cyberwarfare. However, traditional open source benchmarks are not fit for the task, due to the associated…
The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…
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…
Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for…
This paper presents AutoEval, a novel benchmark for scaling Large Language Model (LLM) assessment in formal tasks with clear notions of correctness, such as truth maintenance in translation and logical reasoning. AutoEval is the first…
This document summarizes the experience of Julien Voisin during the 2011 edition of the well-known \emph{Google Summer of Code}. This project is a first step in the domain of metadata anonymization in Free Software. This article is…
The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data,…
Rather than anonymizing social graphs by generalizing them to super nodes/edges or adding/removing nodes and edges to satisfy given privacy parameters, recent methods exploit the semantics of uncertain graphs to achieve privacy protection…
Most of the existing speaker anonymization research has focused on single-speaker audio, leading to the development of techniques and evaluation metrics optimized for such condition. This study addresses the significant challenge of speaker…
Background knowledge is an important factor in privacy preserving data publishing. Distribution-based background knowledge is one of the well studied background knowledge. However, to the best of our knowledge, there is no existing work…
The applicability of process mining techniques hinges on the availability of event logs capturing the execution of a business process. In some use cases, particularly those involving customer-facing processes, these event logs may contain…
Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text.…
Academic publications of latest research results are crucial to advance the development of all disciplines. However, there are several severe disadvantages in current academic publication systems. The first is the misconduct during the…
Speech synthesis, voice cloning, and voice conversion techniques present severe privacy and security threats to users of voice user interfaces (VUIs). These techniques transform one or more elements of a speech signal, e.g., identity and…