Related papers: Deception by Design: Evidence-Based Signaling Game…
Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…
A major challenge in cyber-threat analysis is combining information from different sources to find the person or the group responsible for the cyber-attack. It is one of the most important technical and policy challenges in cyber-security.…
Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…
In the field of network security, the concept of honeypots is well established in research as well as in production. Honeypots are used to imitate a legitimate target on the network and to raise an alert on any interaction. This does not…
We consider the problem of predicting human players' actions in repeated strategic interactions. Our goal is to predict the dynamic step-by-step behavior of individual players in previously unseen games. We study the ability of neural…
Advanced persistent threats (APT) combine a variety of different attack forms ranging from social engineering to technical exploits. The diversity and usual stealthiness of APT turns them into a central problem of contemporary practical…
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…
Communication plays a major role in social systems. Effective communications, which requires transmission of the messages between individuals without disruptions or noise, can be a powerful tool to deliver intended impact. Language and…
Systems operating in adversarial environments may inadvertently leak sensitive information to adversaries. To address this challenge, we revisit the linear-quadratic control framework and introduce deception to actively mislead adversaries.…
Coding theory revolves around the incorporation of redundancy into transmitted symbols, computation tasks, and stored data to guard against adversarial manipulation. However, error correction in coding theory is contingent upon a strict…
Phishing is an online identity theft that aims to steal sensitive information such as username, passwords and online banking details from its victims. Phishing education needs to be considered as a means to combat this threat. This book…
Are current language models capable of deception and lie detection? We study this question by introducing a text-based game called $\textit{Hoodwinked}$, inspired by Mafia and Among Us. Players are locked in a house and must find a key to…
Cybercrime is estimated to cost the global economy almost \$10 trillion annually and with businesses and governments reporting an ever-increasing number of successful cyber-attacks there is a growing demand to rethink the strategy towards…
Honeypots are designed to trap the attacker with the purpose of investigating its malicious behavior. Owing to the increasing variety and sophistication of cyber attacks, how to capture high-quality attack data has become a challenge in the…
A repeated game is an effective tool to model interactions and conflicts for players aiming to achieve their objectives in a long-term basis. Contrary to static noncooperative games that model an interaction among players in only one…
The increasing instances of advanced attacks call for a new defense paradigm that is active, autonomous, and adaptive, named as the \texttt{`3A'} defense paradigm. This chapter introduces three defense schemes that actively interact with…
Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…
Protecting against adversarial attacks is a common multiagent problem. Attackers in the real world are predominantly human actors, and the protection methods often incorporate opponent models to improve the performance when facing humans.…
Sender-receiver games are simple models of information transmission that provide a formalism to study the evolution of honest signaling and deception between a sender and a receiver. In many practical scenarios, lies often affect groups of…