Related papers: Single-Component Privacy Guarantees in Helper Data…
A private compression design problem is studied, where an encoder observes useful data $Y$, wishes to compress it using variable length code and communicates it through an unsecured channel. Since $Y$ is correlated with private attribute…
This work aims to show the applicability, and how, of privacy by design approach to biometric systems and the benefit of using formal methods to this end. Starting from a general framework that has been introduced at STM in 2014, that…
Electronic information is increasingly often shared among entities without complete mutual trust. To address related security and privacy issues, a few cryptographic techniques have emerged that support privacy-preserving information…
Deeply-learned face representations enable the success of current face recognition systems. Despite the ability of these representations to encode the identity of an individual, recent works have shown that more information is stored…
Information hiding technology utilizes the insensitivity of human sensory organs to redundant data, hiding confidential information in the redundant data of these public digital media, and then transmitting it. The carrier media after…
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…
Training data privacy has been a top concern in AI modeling. While methods like differentiated private learning allow data contributors to quantify acceptable privacy loss, model utility is often significantly damaged. In practice,…
Real network datasets provide significant benefits for understanding phenomena such as information diffusion or network evolution. Yet the privacy risks raised from sharing real graph datasets, even when stripped of user identity…
An information-theoretic privacy mechanism design is studied, where an agent observes useful data $Y$ which is correlated with the private data $X$. The agent wants to reveal the information to a user, hence, the agent utilizes a privacy…
Private selection algorithms, such as the Exponential Mechanism, Noisy Max and Sparse Vector, are used to select items (such as queries with large answers) from a set of candidates, while controlling privacy leakage in the underlying data.…
This is a paper about private data analysis, in which a trusted curator holding a confidential database responds to real vector-valued queries. A common approach to ensuring privacy for the database elements is to add appropriately…
Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…
This paper proposes to study the impact of image selective encryption on both forensics and privacy preserving mechanisms. The proposed selective encryption scheme works independently on each bitplane by encrypting the s most significant…
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…
Privacy-preserving data splitting is a technique that aims to protect data privacy by storing different fragments of data in different locations. In this work we give a new combinatorial formulation to the data splitting problem. We see the…
This paper studies the statistical characterization of detecting an adversary who wants to harm some computation such as machine learning models or aggregation by altering the output of a differentially private mechanism in addition to…
Designing a data sharing mechanism without sacrificing too much privacy can be considered as a game between data holders and malicious attackers. This paper describes a compressive adversarial privacy framework that captures the trade-off…
Feature selection is a technique that extracts a meaningful subset from a set of features in training data. When the training data is large-scale, appropriate feature selection enables the removal of redundant features, which can improve…
This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation…
We study the role of coded side information in single-server Private Information Retrieval (PIR). An instance of the single-server PIR problem includes a server that stores a database of $K$ independently and uniformly distributed messages,…