Related papers: Duplicity Games for Deception Design with an Appli…

Grim-trigger strategies are a fundamental mechanism for sustaining equilibria in iterated games: the players cooperate along an agreed path, and as soon as one player deviates, the others form a coalition to play him down to his minmax…

With the increasing prevalence of security incidents, the adoption of deception-based defense strategies has become pivotal in cyber security. This work addresses the challenge of scalability in designing honeytokens, a key component of…

Cognitive vulnerabilities shape human decision-making and arise primarily from two sources: (1) cognitive capabilities, which include disparities in knowledge, education, expertise, or access to information, and (2) cognitive biases, such…

We develop investment approaches to secure electric power systems against load attacks where a malicious intruder (the attacker) covertly changes reactive power setpoints of loads to push the grid towards voltage instability while the…

We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

This letter presents an approach to guarantee online safety of a cyber-physical system under multiple state and input constraints. Our proposed framework, called gatekeeper, recursively guarantees the existence of an infinite-horizon…

The immune system provides an ideal metaphor for anomaly detection in general and computer security in particular. Based on this idea, artificial immune systems have been used for a number of years for intrusion detection, unfortunately so…

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the…

We study minimum entropy submodular optimization, a common generalization of the minimum entropy set cover problem, studied earlier by Cardinal et al., and the submodular set cover problem. We give a general bound of the approximation…

This paper presents an intelligent and adaptive agent that employs deception to recognize a cyber adversary's intent. Unlike previous approaches to cyber deception, which mainly focus on delaying or confusing the attackers, we focus on…

Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Consensus in multi-agent dynamical systems is prone to be sabotaged by the adversary, which has attracted much attention due to its key role in broad applications. In this paper, we study a new false data injection (FDI) attack design…

As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers,…

In the last years we have witnessed the appearance of a variety of strategies to design optimal location privacy-preserving mechanisms, in terms of maximizing the adversary's expected error with respect to the users' whereabouts. In this…

The recent advancement in real-world critical infrastructure networks has led to an exponential growth in the use of automated devices which in turn has created new security challenges. In this paper, we study the robust and adaptive…

With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine…

This paper studies defense mechanisms against model inversion (MI) attacks -- a type of privacy attacks aimed at inferring information about the training data distribution given the access to a target machine learning model. Existing…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…