Related papers: Honeypot Protocol
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is particularly concerning. To study this, we let a red team…
As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly critical to ensure alignment. While numerous scalable oversight…
We evaluate the propensity of frontier models to sabotage or refuse to assist with safety research when deployed as AI research agents within a frontier AI company. We apply two complementary evaluations to four Claude models (Mythos…
Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…
Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabilities and objectives - also known as scheming. We study whether…
Windows operating systems (OS) are ubiquitous in enterprise Information Technology (IT) and operational technology (OT) environments. Due to their widespread adoption and known vulnerabilities, they are often the primary targets of malware…
Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven…
We study automated security response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed, non-stationary game. We relax the standard assumption that the game model is correctly…
Post-deployment monitoring of artificial intelligence (AI) systems in health care is essential to ensure their safety, quality, and sustained benefit-and to support governance decisions about which systems to update, modify, or…
The great performance of machine learning algorithms and deep neural networks in several perception and control tasks is pushing the industry to adopt such technologies in safety-critical applications, as autonomous robots and self-driving…
Lateral movement of advanced persistent threats has posed a severe security challenge. Due to the stealthy and persistent nature of the lateral movement, defenders need to consider time and spatial locations holistically to discover latent…
The ubiquitous nature of the IoT devices has brought serious security implications to its users. A lot of consumer IoT devices have little to no security implementation at all, thus risking user's privacy and making them target of mass…
Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could…
We present a shared control paradigm that improves a user's ability to operate complex, dynamic systems in potentially dangerous environments without a priori knowledge of the user's objective. In this paradigm, the role of the autonomous…
A combination of deep reinforcement learning and supervised learning is proposed for the problem of active sequential hypothesis testing in completely unknown environments. We make no assumptions about the prior probability, the action and…
The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action while the environment simultaneously chooses an outcome. The…
Internet of Things (IoT) has seen a prolific rise in recent times and provides the ability to solve several key challenges faced by our societies and environment. Data produced by IoT provides a significant opportunity to infer context that…
The design of safe-critical control algorithms for systems under Denial-of-Service (DoS) attacks on the system output is studied in this work. We aim to address scenarios where attack-mitigation approaches are not feasible, and the system…
One of the widely used cyber deception techniques is decoying, where defenders create fictitious machines (i.e., honeypots) to lure attackers. Honeypots are deployed to entice attackers, but their effectiveness depends on their…
Honeypot is an important cyber defense technique that can expose attackers new attacks. However, the effectiveness of honeypots has not been systematically investigated, beyond the rule of thumb that their effectiveness depends on how they…