相关论文: Integrating Sequential Hypothesis Testing into Adv…

As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…

University engineering capstone projects involve sustained interaction among students, faculty, and industry sponsors whose objectives are only partially aligned. While capstones are widely used in engineering education, existing analyses…

Sequential equilibrium is the conventional approach for analyzing multi-stage games of incomplete information. It relies on mutual consistency of beliefs. To relax mutual consistency, I theoretically and experimentally explore the dynamic…

With the increasing sophistication of attacks on cyber-physical systems, deception has emerged as an effective tool to improve system security and safety by obfuscating the attacker's perception. In this paper, we present a solution to the…

Deception is a technique to mislead human or computer systems by manipulating beliefs and information. Successful deception is characterized by the information-asymmetric, dynamic, and strategic behaviors of the deceiver and the deceivee.…

Given the complexity of multi-tenant cloud environments and the growing need for real-time threat mitigation, Security Operations Centers (SOCs) must adopt AI-driven adaptive defense mechanisms to counter Advanced Persistent Threats (APTs).…

Driven by recent successes in two-player, zero-sum game solving and playing, artificial intelligence work on games has increasingly focused on algorithms that produce equilibrium-based strategies. However, this approach has been less…

Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade. In this paper, we report our ongoing effort to integrate these two presently distinct areas into a single…

In this paper, we employ a hypergame framework to analyze the single-leader-multiple-followers (SLMF) Stackelberg security game with two typical misinformed situations: misperception and deception. We provide a stability criterion with the…

The dual offensive and defensive utility of Large Language Models (LLMs) highlights a critical gap in AI security: the lack of unified frameworks for dynamic, iterative adversarial adaptation hardening. To bridge this gap, we propose the…

In this short note, we propose a unified framework that bridges three areas: (1) a flipped perspective on the Turing Test, the "dual Turing test", in which a human judge's goal is to identify an AI rather than reward a machine for…

Stochastic dynamic teams and games are rich models for decentralized systems and challenging testing grounds for multi-agent learning. Previous work that guaranteed team optimality assumed stateless dynamics, or an explicit coordination…

We study a cooperative game in which each member of a team of $N$ players, wearing coloured hats and situated at the vertices of a cycle graph $C_N$, is guessing their own hat colour merely on the basis of observing the hats worn by their…

Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We stress-tested sandbagging detection techniques using an auditing game. First, a red team fine-tuned…

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…

Data injection attacks have recently emerged as a significant threat on the smart power grid. By launching data injection attacks, an adversary can manipulate the real-time locational marginal prices to obtain economic benefits. Despite the…

Ensuring robust decision-making in multi-agent systems is challenging when agents have distinct, possibly conflicting objectives and lack full knowledge of each other's strategies. This is apparent in safety-critical applications such as…

An underlying assumption of Stackelberg Games (SGs) is perfect rationality of the players. However, in real-life situations (which are often modeled by SGs) the followers (terrorists, thieves, poachers or smugglers) -- as humans in general…

This paper argues that the finite horizon paradox, where game theory contradicts intuition, stems from the limitations of standard number systems in modelling the cognitive perception of infinity. To address this issue, we propose a new…

The growing complexity and interconnectivity of Intelligent Transportation Systems (ITS) make them increasingly vulnerable to advanced cyber threats, particularly deceptive information attacks. These sophisticated threats exploit…