Related papers: Duplicity Games for Deception Design with an Appli…
Learning in multi-player games can model a large variety of practical scenarios, where each player seeks to optimize its own local objective function, which at the same time relies on the actions taken by others. Motivated by the frequent…
We present a method to automatically find security strategies for the use case of intrusion prevention. Following this method, we model the interaction between an attacker and a defender as a Markov game and let attack and defense…
This paper proposes a game-theoretic approach to address the problem of optimal sensor placement against an adversary in uncertain networked control systems. The problem is formulated as a zero-sum game with two players, namely a malicious…
Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…
Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about the safety,…
The nodes of a regular two-dimensional lattice play a game based on the joint action of two distinct levels. At the first step of the game, using a random prescription half players are assigned the cooperation and half the defection state.…
How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…
In large-scale networks, communication links between nodes are easily injected with false data by adversaries. This paper proposes a novel security defense strategy from the perspective of attack detection scheduling to ensure the security…
Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…
How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…
Can deception exist in differential games? We provide a case study for a Turret-Attacker differential game, where two Attackers seek to score points by reaching a target region while a Turret tries to minimize the score by aligning itself…
Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this…
As large language models (LLMs) continue to evolve, their potential use in automating cyberattacks becomes increasingly likely. With capabilities such as reconnaissance, exploitation, and command execution, LLMs could soon become integral…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…
While Deep Neural Networks (DNNs) excel in many tasks, the huge training resources they require become an obstacle for practitioners to develop their own models. It has become common to collect data from the Internet or hire a third party…
Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, agents must allocate…
Cyber-Physical Systems (CPSs) are facing a fast-growing wave of attacks. To achieve effective proactive defense, this paper models honeypot deployment as a gamma-fixed signaling game in which node liveness serves as the only signal and…
Inspired by scenarios where the strategic network design and defense or immunisation are of the central importance, Goyal et al. [3] defined a new Network Formation Game with Attack and Immunisation. The authors showed that despite the…
Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require substituting the original GNNs with defense models, regardless…
A honeypot is a type of security facility deliberately created to be probed, attacked and compromised. It is often used for protecting production systems by detecting and deflecting unauthorized accesses. It is also useful for investigating…