相关论文: Protecting and Preserving Protest Dynamics for Res…

While power systems research relies on the availability of real-world network datasets, data owners (e.g., system operators) are hesitant to share data due to security and privacy risks. To control these risks, we develop privacy-preserving…

Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…

Recently, generative AI has attracted much attention from both academic and industrial fields, which has shown its potential, especially in the data generation and synthesis aspects. Simultaneously, secure and privacy-preserving mobile…

The large number of publicly available survey datasets of wide variety, albeit useful, raise respondent-level privacy concerns. The synthetic data approach to data privacy and confidentiality has been shown useful in terms of privacy…

Natural disasters affect hundreds of millions of people worldwide every year. Early warning, humanitarian response and recovery mechanisms can be improved by using big data sources. Measuring the different dimensions of the impact of…

Open data sets that contain personal information are susceptible to adversarial attacks even when anonymized. By performing low-cost joins on multiple datasets with shared attributes, malicious users of open data portals might get access to…

Synthetic data, which is artificially generated and intelligently mimicking or supplementing the real-world data, is increasingly used. The proliferation of AI agents and the adoption of synthetic data create a synthetic mirror that…

We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive…

Differential privacy (DP) enables safe data release, with synthetic data generation emerging as a common approach in recent years. Yet standard synthesizers preserve all dependencies in the data, including spurious correlations between…

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use of medical data and…

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not…

AI-synthesized faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts. Although progress has been made in developing…

In many practical applications of differential privacy, practitioners seek to provide the best privacy guarantees subject to a target level of accuracy. A recent line of work by Ligett et al. '17 and Whitehouse et al. '22 has developed such…

We collect and analyse messages exchanged in Twitter using two of the platform's publicly available APIs (the search and stream specifications). We assess the differences between the two samples, and compare the networks of communication…

Data forms the backbone of artificial intelligence (AI). Privacy and data protection laws thus have strong bearing on AI systems. Shielded by the rhetoric of compliance with data protection and privacy regulations, privacy-preserving…

Artificial intelligence (AI) is transforming supply chain management, yet progress in predictive tasks -- such as delivery delay prediction -- remains constrained by the scarcity of high-quality, openly available datasets. Existing datasets…

As Artificial Intelligence (AI) systems become increasingly integrated into various aspects of daily life, concerns about privacy and ethical accountability are gaining prominence. This study explores stakeholder perspectives on privacy in…

Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k…