Related papers: Probabilistic Anonymity and Admissible Schedulers

The structure of network data enables simple predictive models to leverage local correlations between nodes to high accuracy on tasks such as attribute and link prediction. While this is useful for building better user models, it introduces…

There are currently two approaches to anonymization: "utility first" (use an anonymization method with suitable utility features, then empirically evaluate the disclosure risk and, if necessary, reduce the risk by possibly sacrificing some…

Organizations use privacy policies to communicate their data collection practices to their clients. A privacy policy is a set of statements that specifies how an organization gathers, uses, discloses, and maintains a client's data. However,…

Inspired by privacy problems where the behavior of a system should not be revealed to an external curious observer, we investigate event concealment and concealability enforcement in discrete event systems modeled as non-deterministic…

This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb…

Attacks on classical cryptographic protocols are usually modeled by allowing an adversary to ask queries from an oracle. Security is then defined by requiring that as long as the queries satisfy some constraint, there is some problem the…

Two styles of definitions are usually considered to express that a security protocol preserves the confidentiality of a data s. Reachability-based secrecy means that s should never be disclosed while equivalence-based secrecy states that…

The current privacy evaluation for speaker anonymization often overestimates privacy when a same-gender target selection algorithm (TSA) is used, although this TSA leaks the speaker's gender and should hence be more vulnerable. We…

In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an…

Modern classification algorithms are susceptible to adversarial examples--perturbations to inputs that cause the algorithm to produce undesirable behavior. In this work, we seek to understand and extend adversarial examples across domains…

The model of camera that was used to capture a particular photographic image (model attribution) is typically inferred from high-frequency model-specific artifacts present within the image. Model anonymization is the process of transforming…

A paper presented at the ICICS 2019 conference describes what is claimed to be a `provably secure group authentication [protocol] in the asynchronous communication model'. We show here that this is far from being the case, as the protocol…

We study secure and undetectable communication in a world where governments can read all encrypted communications of citizens. We consider a world where the only permitted communication method is via a government-mandated encryption scheme,…

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to evade detection by…

Unawareness of privacy risks together with approval seeking motivations make humans enter too much detail into the likes of Facebook, Twitter, and Instagram. To test whether the rationality principle applies, we construct a tool that shows…

The privacy of machine learning models has become a significant concern in many emerging Machine-Learning-as-a-Service applications, where prediction services based on well-trained models are offered to users via pay-per-query. The lack of…

Many auction settings implicitly or explicitly require that bidders are treated equally ex-ante. This may be because discrimination is philosophically or legally impermissible, or because it is practically difficult to implement or…

Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…

Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distribution coverage. Accordingly, proposals are made for…

This paper describes a new protocol for authentication in ad-hoc networks. The protocol has been designed to meet specialized requirements of ad-hoc networks, such as lack of direct communication between nodes or requirements for revocable…