Related papers: A Note on the Misinterpretation of the US Census R…
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…
A tremendous amount of individual-level data is generated each day, of use to marketing, decision makers, and machine learning applications. This data often contain private and sensitive information about individuals, which can be disclosed…
This work explores an emerging security threat against deep neural networks (DNNs) based image classification, i.e., backdoor attack. In this scenario, the attacker aims to inject a backdoor into the model by manipulating training data,…
AI-based face recognition, i.e., the re-identification of individuals within images, is an already well established technology for video surveillance, for user authentication, for tagging photos of friends, etc. This paper demonstrates that…
In this paper, a new randomized response technique aimed at protecting respondents' privacy is proposed. It is designed for estimating the population total, or the population mean, of a quantitative characteristic. It provides a~high degree…
Biometric systems, such as face recognition systems powered by deep neural networks (DNNs), rely on large and highly sensitive datasets. Backdoor attacks can subvert these systems by manipulating the training process. By inserting a small…
While extremely useful (e.g., for COVID-19 forecasting and policy-making, urban mobility analysis and marketing, and obtaining business insights), location data collected from mobile devices often contain data from a biased population…
Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details. However, prevailing person re-identification(re-ID) methods use…
Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…
The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and the cloud to reduce latency and protect user privacy.…
As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user images. The widely adopted technology uses local feature descriptors, which are…
Re-identification algorithms are used in data privacy to measure disclosure risk. They model the situation in which an adversary attacks a published database by means of linking the information of this adversary with the database. In this…
Federated Learning (FL) trains a black-box and high-dimensional model among different clients by exchanging parameters instead of direct data sharing, which mitigates the privacy leak incurred by machine learning. However, FL still suffers…
Social media data provides propitious opportunities for public health research. However, studies suggest that disparities may exist in the representation of certain populations (e.g., people of lower socioeconomic status). To quantify and…
Recently, Person Re-Identification (Re-ID) has received a lot of attention. Large datasets containing labeled images of various individuals have been released, allowing researchers to develop and test many successful approaches. However,…
Deep neural networks (DNNs) are now the de facto choice for computer vision tasks such as image classification. However, their complexity and "black box" nature often renders the systems they're deployed in vulnerable to a range of security…
The use of formal privacy to protect the confidentiality of responses in the 2020 Decennial Census of Population and Housing has triggered renewed interest and debate over how to measure the disclosure risks and societal benefits of the…
Detailed estimates of migration stocks and flows provides evidence for understanding population dynamics, and the impact of economic and political changes that influence migration. Using data from the 2000 decennial census and 2001-2016…
In deep neural networks for facial recognition, feature vectors are numerical representations that capture the unique features of a given face. While it is known that a version of the original face can be recovered via "feature…
Networked system often relies on distributed algorithms to achieve a global computation goal with iterative local information exchanges between neighbor nodes. To preserve data privacy, a node may add a random noise to its original data for…