Related papers: Blind De-anonymization Attacks using Social Networ…

We revisit the privacy-utility tradeoff of x-vector speaker anonymization. Existing approaches quantify privacy through training complex speaker verification or identification models that are later used as attacks. Instead, we propose a…

Benefiting from its superior feature learning capabilities and efficiency, deep hashing has achieved remarkable success in large-scale image retrieval. Recent studies have demonstrated the vulnerability of deep hashing models to backdoor…

To prove that a dataset is sufficiently anonymized, many privacy policies suggest that a re-identification risk assessment be performed, but do not provide a precise methodology for doing so, leaving the industry alone with the problem.…

Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that…

Skeleton-based action recognition attracts practitioners and researchers due to the lightweight, compact nature of datasets. Compared with RGB-video-based action recognition, skeleton-based action recognition is a safer way to protect the…

We consider the privacy of interactions between individuals in a network. For many networks, while nodes are anonymous to outside observers, the existence of a link between individuals implies the possibility of one node revealing…

Centralized social networks have experienced a transformative impact on our digital era communication, connection, and information-sharing information. However, it has also raised significant concerns regarding users' privacy and individual…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has…

This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the sensor data have different underlying…

Smart meters, devices measuring the electricity and gas consumption of a household, are currently being deployed at a fast rate throughout the world. The data they collect are extremely useful, including in the fight against climate change.…

Differential privacy offers formal quantitative guarantees for algorithms over datasets, but it assumes attackers that know and can influence all but one record in the database. This assumption often vastly overapproximates the attackers'…

This work proposes and analyzes the use of keystroke biometrics for content de-anonymization. Fake news have become a powerful tool to manipulate public opinion, especially during major events. In particular, the massive spread of fake news…

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

There are a number of vectors for attack when trying to link an individual to a certain DNA sequence. Phenotypic prediction is one such vector; linking DNA to an individual based on their traits. Current approaches are not overly effective,…

DNA sequencing is becoming increasingly commonplace, both in medical and direct-to-consumer settings. To promote discovery, collected genomic data is often de-identified and shared, either in public repositories, such as OpenSNP, or with…

Over the last decade there have been great strides made in developing techniques to compute functions privately. In particular, Differential Privacy gives strong promises about conclusions that can be drawn about an individual. In contrast,…

This paper introduces a unified computational framework for the anonymization problem in social networks, where the objective is to maximize node anonymity through graph alterations. We define three variants of the underlying optimization…

The unprecedented capture and application of face images raise increasing concerns on anonymization to fight against privacy disclosure. Most existing methods may suffer from the problem of excessive change of the identity-independent…

This work considers the fundamental privacy limits under active fingerprinting attacks in power-law bipartite networks. The scenario arises naturally in social network analysis, tracking user mobility in wireless networks, and forensics…