Related papers: Password-Activated Shutdown Protocols for Misalign…

The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might need to verify that powerful AI models are widely deployed…

Modern artificial intelligence governance lacks a formal, enforceable mechanism for determining whether a given AI system is legally permitted to operate in a specific domain and jurisdiction. Existing tools such as model cards, audits, and…

If we wish to compromise some password-protected system as an attacker (i.e. a member of the red team), we have a large number of popular and actively-maintained tools to choose from in helping us to realise our goal. Password hash cracking…

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

Building trustworthy autonomous systems is challenging for many reasons beyond simply trying to engineer agents that 'always do the right thing.' There is a broader context that is often not considered within AI and HRI: that the problem of…

Mitigating the risks from frontier AI systems requires up-to-date and reliable information about those systems. Organizations that develop and deploy frontier systems have significant access to such information. By reporting safety-critical…

The widespread adoption of Reconfigurable Intelligent Surfaces (RISs) in future practical wireless systems is critically dependent on the integration of the RIS into higher-layer protocols beyond the physical (PHY) one, an issue that has…

Cloud-based Artificial Intelligence (AI) inference is increasingly latency- and context-sensitive, yet today's AI-as-a-Service is typically consumed as an application-chosen endpoint, leaving the network to provide only best-effort…

AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show…

Collaborative AI systems (CAISs) aim at working together with humans in a shared space to achieve a common goal. This critical setting yields hazardous circumstances that could harm human beings. Thus, building such systems with strong…

Multi-agent systems (MAS) powered by artificial intelligence (AI) are increasingly foundational to complex, distributed workflows. Yet, the security of their underlying communication protocols remains critically under-examined. This paper…

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dynamic and interaction-dependent process that heavily depends on the social environment where agents are deployed, either collaborative,…

As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on…

Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents suffer from critical inefficiency: they conduct excessive…

The rapid advancements in wireless technology have significantly increased the demand for communication resources, leading to the development of Spectrum Access Systems (SAS). However, network regulations require disclosing sensitive user…

A multi-agent AI system (MAS) is composed of multiple autonomous agents that interact, exchange information, and make decisions based on internal generative models. Recent advances in large language models and tool-using agents have made…

Open-weight advanced AI models -- systems whose parameters are freely available for download and adaptation -- are reshaping the global AI landscape. As these models rapidly close the performance gap with closed alternatives, they enable…

Enterprises and organizations today increasingly deploy in-house, cloud based applications and APIs for internal operations or external customers. These deployments deal with increasing number of threats, despite security features offered…

The protection of non-combatants in times of (fully) autonomous warfare raises the question of the timeliness of the international protective emblem. Incidents in the recent past indicate that it is becoming necessary to transfer the…

International institutions may have an important role to play in ensuring advanced AI systems benefit humanity. International collaborations can unlock AI's ability to further sustainable development, and coordination of regulatory efforts…