相关论文: PRIVEE: A Visual Analytic Workflow for Proactive P…
Recent advances in computing have allowed for the possibility to collect large amounts of data on personal activities and private living spaces. To address the privacy concerns of users in this environment, we propose a novel framework…
This paper aims to shed light on the ethical problems of creating and deploying computer vision tech, particularly in using publicly available datasets. Due to the rapid growth of machine learning and artificial intelligence, computer…
Defining privacy and related notions such as Personal Identifiable Information (PII) is a central notion in computer science and other fields. The theoretical, technological, and application aspects of PII require a framework that provides…
Openly sharing data with sensitive attributes and privacy restrictions is a challenging task. In this document we present the implementation of pyCANON, a Python library and command line interface (CLI) to check and assess the level of…
Valuable insights, such as frequently visited environments in the wake of the COVID-19 pandemic, can oftentimes only be gained by analyzing sensitive data spread across edge-devices like smartphones. To facilitate such an analysis, we…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk…
Fifty study participants playtested an innocent-looking "escape room" game in virtual reality (VR). Within just a few minutes, an adversarial program had accurately inferred over 25 of their personal data attributes, from anthropometrics…
We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given that large-scale datasets are often sourced from the internet,…
We study the problem of concealing functionality of a proprietary or private module when provenance information is shown over repeated executions of a workflow which contains both `public' and `private' modules. Our approach is to use…
Sensitive data release is vulnerable to output-side privacy threats such as membership inference, attribute inference, and record linkage. This creates a practical need for release mechanisms that provide formal privacy guarantees while…
The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
Collecting personally identifiable information (PII) on data subjects has become big business. Data brokers and data processors are part of a multi-billion-dollar industry that profits from collecting, buying, and selling consumer data. Yet…
With the emergence of smart cities, Internet of Things (IoT) devices as well as deep learning technologies have witnessed an increasing adoption. To support the requirements of such paradigm in terms of memory and computation, joint and…
We study an information theoretic privacy mechanism design problem for two scenarios where the private data is either observable or hidden. In each scenario, we first consider bounded mutual information as privacy leakage criterion, then we…
With the advent of numerous online content providers, utilities and applications, each with their own specific version of privacy policies and its associated overhead, it is becoming increasingly difficult for concerned users to manage and…
Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by…
The design of a statistical signal processing privacy problem is studied where the private data is assumed to be observable. In this work, an agent observes useful data $Y$, which is correlated with private data $X$, and wants to disclose…
To protect user privacy in data analysis, a state-of-the-art strategy is differential privacy in which scientific noise is injected into the real analysis output. The noise masks individual's sensitive information contained in the dataset.…