Related papers: Rationality is Self-Defeating in Permissionless Sy…
This position paper argues for metacognition as a general design principle for creating more accurate, secure, and efficient AI. The metacognitive solution involves systems monitoring their own states and judiciously allocating resources…
Classical higher-order logic, when utilized as a meta-logic in which various other (classical and non-classical) logics can be shallowly embedded, is well suited for realising a universal logic reasoning approach. Universal logic reasoning…
Many complex systems may be described not by one, but by a number of complex networks mapped one on the other in a multilayer structure. The interactions and dependencies between these layers cause that what is true for a distinct single…
It is known that a two-dimensional $F$-rational ring has a rational singularity. However a two-dimensional ring with a rational singularity is not $F$-rational in general. In this paper, we investigate $F$-rationality of a two-dimensional…
Transparency is often deemed critical to enable effective real-world deployment of intelligent systems. Yet the motivations for and benefits of different types of transparency can vary significantly depending on context, and objective…
In this paper, we introduce a formal notion of partial compliance, called Attack-resistance, of a computer program running together with a defense mechanism w.r.t a non-exploitability specification. In our setting, a program may contain…
Rationality has been an intriguing topic for several decades. Even the scope of definition of rationality across different subjects varies. Several theories (e.g., game theory) initially evolved on the basis that agents (e.g., humans) are…
Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we investigate why safety…
Hybrid systems are integrations of discrete computation and continuous physical evolution. The physical components of such systems introduce safety requirements, the achievement of which asks for the correct monitoring and control from the…
To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…
Cybersecurity planning supports the selection of and implementation of security controls in resource-constrained settings to manage risk. Doing so requires considering adaptive adversaries with different levels of strategic sophistication…
Is more information always better? Or are there some situations in which more information can make us worse off? Good (1967) argues that expected utility maximizers should always accept more information if the information is cost-free and…
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…
Even though classic theories and models of discrete choice pose man as a rational being, it has been shown extensively that people persistently violate rationality in their actual choices. Recent models of decision-making take these…
Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…
We consider the problem of rational decision making in the presence of nonlinear constraints. By using tools borrowed from spin glass and random matrix theory, we focus on the portfolio optimisation problem. We show that the number of…
We propose a formal framework for intelligent systems which can reason about scientific domains, in particular about the carcinogenicity of chemicals, and we study its properties. Our framework is grounded in a philosophy of scientific…
Causal questions often permeate in our day-to-day activities. With causal reasoning and counterfactual intuition, privacy threats can not only be alleviated but also prevented. In this paper, we discuss what is causal and counterfactual…
A cautious interpretation of AI regulations and policy in the EU and the USA place explainability as a central deliverable of compliant AI systems. However, from a technical perspective, explainable AI (XAI) remains an elusive and complex…
In many situations humans have to reason with inconsistent knowledge. These inconsistencies may occur due to not fully reliable sources of information. In order to reason with inconsistent knowledge, it is not possible to view a set of…