Related papers: Leakage and Protocol Composition in a Game-Theoret…

Cyber attacks continue to be a cause of concern despite advances in cyber defense techniques. Although cyber attacks cannot be fully prevented, standard decision-making frameworks typically focus on how to prevent them from succeeding,…

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…

This thesis addresses the foundational aspects of formal methods for applications in security and in particular in anonymity. More concretely, we develop frameworks for the specification of anonymity properties and propose algorithms for…

Federated learning systems increasingly rely on diverse network topologies to address scalability and organizational constraints. While existing privacy research focuses on gradient-based attacks, the privacy implications of network…

In cybersecurity, attackers range from brash, unsophisticated script kiddies and cybercriminals to stealthy, patient advanced persistent threats. When modeling these attackers, we can observe that they demonstrate different risk-seeking and…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

We consider linear-quadratic-Gaussian (LQG) network games in which agents have quadratic payoffs that depend on their individual and neighbors' actions, and an unknown payoff-relevant state. An information designer determines the fidelity…

Game theory is appropriate for studying cyber conflict because it allows for an intelligent and goal-driven adversary. Applications of game theory have led to a number of results regarding optimal attack and defense strategies. However, the…

We consider a cascade network where a sequence of nodes each send a message to their downstream neighbor to enable coordination, the first node having access to an information signal. An adversary also receives all of the communication as…

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…

The vulnerabilities of deep learning models towards adversarial attacks have attracted increasing attention, especially when models are deployed in security-critical domains. Numerous defense methods, including reactive and proactive ones,…

Financial, social, and political factors often prevent the interests of the owners of ML systems and services and their users from being perfectly aligned. ML systems often produce biased information that can influence users to make…

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…

As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data.…

Advanced persistent threats (APTs) are organized prolonged cyberattacks by sophisticated attackers. Although APT activities are stealthy, they interact with the system components and these interactions lead to information flows. Dynamic…

A quantum protocol is described which enables a user to send sealed messages and that allows for the detection of active eavesdroppers. We examine a class of eavesdropping strategies, those that make use of quantum operations, and we…

We discuss a duel-type game in which Player I uses his resource continuously and Player II distributes it by discrete portions. Each player knows how much resources he and his opponent have at every moment of time. The solution of the game…

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

Large language model-based (LLM-based) agents have become common in settings that include non-cooperative parties. In such settings, agents' decision-making needs to conceal information from their adversaries, reveal information to their…