Related papers: Probabilistic Anonymity and Admissible Schedulers
Opacity is a property expressing whether a system may reveal its secret to a passive observer (an intruder) who knows the structure of the system but has a limited observation of its behavior. Several notions of opacity have been studied,…
Decentralized coordination is one of the fundamental challenges for societies and organizations. While extensively explored from a variety of perspectives, one issue which has received limited attention is human coordination in the presence…
In several settings of practical interest, two parties seek to collaboratively perform inference on their private data using a public machine learning model. For instance, several hospitals might wish to share patient medical records for…
The phenomenon of Adversarial Examples is attracting increasing interest from the Machine Learning community, due to its significant impact to the security of Machine Learning systems. Adversarial examples are similar (from a perceptual…
Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…
Users like sharing personal photos with others through social media. At the same time, they might want to make automatic identification in such photos difficult or even impossible. Classic obfuscation methods such as blurring are not only…
This paper presents new methods enabling anonymous communication on the Internet. We describe a new protocol that allows us to create an anonymous overlay network by exploiting the web browsing activities of regular users. We show that the…
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning…
Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to…
Timing side channels in two-user schedulers are studied. When two users share a scheduler, one user may learn the other user's behavior from patterns of service timings. We measure the information leakage of the resulting timing side…
Cyber-secure networked control is modeled, analyzed, and experimentally illustrated in this paper. An attack space defined by the adversary's system knowledge, disclosure, and disruption resources is introduced. Adversaries constrained by…
We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
Anonymity and privacy are two key properties of modern communication networks. In quantum networks, distributed quantum sensing has emerged as a powerful use case, with applications to clock synchronisation, detecting gravitational effects…
Population protocols are a distributed computation model in which a collection of anonymous, finite-state agents interact in randomly chosen pairs and update their states according to a fixed transition function. The computation is defined…
This paper is concerned with a binary detection problem over a non-secure network. To satisfy the communication rate constraint and against possible cyber attacks, which are modeled as deceptive signals injected to the network, a likelihood…
Data anonymization is an approach to privacy-preserving data release aimed at preventing participants reidentification, and it is an important alternative to differential privacy in applications that cannot tolerate noisy data. Existing…
Opacity is a security property formalizing the information leakage of a system to an external observer, namely intruder. The conventional opacity that has been studied in the Discrete Event System (DES) literature usually assumes passive…
We investigate the challenge of establishing stochastic-like guarantees when sequentially learning from a stream of i.i.d. data that includes an unknown quantity of clean-label adversarial samples. We permit the learner to abstain from…
Adversarial training was introduced as a way to improve the robustness of deep learning models to adversarial attacks. This training method improves robustness against adversarial attacks, but increases the models vulnerability to privacy…