Related papers: Reasoning Under Threat: Symbolic and Neural Techni…
As AI systems approach dangerous capability levels where inability safety cases become insufficient, we need alternative approaches to ensure safety. This paper presents a roadmap for constructing safety cases based on chain-of-thought…
We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails,…
Autonomous systems -- such as self-driving cars, autonomous drones, and automated trains -- must come with strong safety guarantees. Over the past decade, techniques based on formal methods have enjoyed some success in providing strong…
Cybersecurity threat and risk analysis (RA) approaches are used to identify and mitigate security risks early-on in the software development life-cycle. Existing approaches automate only parts of the analysis procedure, leaving key…
Principled accountability in the aftermath of harms is essential to the trustworthy design and governance of algorithmic decision making. Legal theory offers a paramount method for assessing culpability: putting the agent 'on the stand' to…
Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming. However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance-and…
As large language models (LLMs) are increasing integrated into fact-checking pipelines, formal logic is often proposed as a rigorous means by which to mitigate bias, errors and hallucinations in these models' outputs. For example, some…
In this work we introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context, along with a variant of the Rational Speech Act (RSA) framework which we call…
Explainable AI (XAI) holds significant promise for enhancing the transparency and trustworthiness of AI-driven threat detection in Security Operations Centers (SOCs). However, identifying the appropriate level and format of explanation,…
Due to the variety of cyber-attacks or threats, the cybersecurity community enhances the traditional security control mechanisms to an advanced level so that automated tools can encounter potential security threats. Very recently, Cyber…
This, with the ever-increasing sophistication of cyberwar, calls for novel solutions. In this regard, Large Language Models (LLMs) have emerged as a highly promising tool for defensive and offensive cybersecurity-related strategies. While…
Testing object detectors in safety-critical domains requires semantically meaningful probes beyond pixel-level corruptions. We present SemProbe, a tool for semantic robustness probing: users upload deployment images, create masks manually…
Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving…
Language is not neutral; it frames understanding, structures power, and shapes governance. This paper argues that misnomers like cybersecurity and artificial intelligence (AI) are more than semantic quirks; they carry significant governance…
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…
Although automated reasoning with diagrams has been possible for some years, tools for diagrammatic reasoning are generally much less sophisticated than their sentential cousins. The tasks of exploring levels of automation and abstraction…
Artificial intelligence (AI) has been advancing at a fast pace and it is now poised for deployment in a wide range of applications, such as autonomous systems, medical diagnosis and natural language processing. Early adoption of AI…
In the dynamic realm of cybersecurity, awareness training is crucial for strengthening defenses against cyber threats. This survey examines a spectrum of cybersecurity awareness training methods, analyzing traditional, technology-based, and…
Experimental research methods describe standards to safeguard scientific integrity and reputability. These methods have been extensively integrated into traditional scientific disciplines and studied in the philosophy of science. The field…