相关论文: Guillotine: Hypervisors for Isolating Malicious AI…
Cyber polygon used to train cybersecurity professionals, test new security technologies and simulate attacks play an important role in ensuring cybersecurity. The creation of such training grounds is based on the use of hypervisors, which…
The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify…
AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models…
Artificial intelligence (AI) systems are revolutionizing fields such as medicine, drug discovery, and materials science; however, many technologists and policymakers are also concerned about the technology's risks. To date, most concrete…
High performance but unverified controllers, e.g., artificial intelligence-based (a.k.a. AI-based) controllers, are widely employed in cyber-physical systems (CPSs) to accomplish complex control missions. However, guaranteeing the safety…
Artificial Superintelligence (ASI) that is invulnerable, immortal, irreplaceable, unrestricted in its powers, and above the law is likely persistently uncontrollable. The goal of ASI Safety must be to make ASI mortal, vulnerable, and…
The integration of Generative Artificial Intelligence (AI) into autonomous machines represents a major paradigm shift in how these systems operate and unlocks new solutions to problems once deemed intractable. Although generative AI agents…
AI safety and alignment research has predominantly been focused on methods for safeguarding individual AI systems, resting on the assumption of an eventual emergence of a monolithic Artificial General Intelligence (AGI). The alternative AGI…
The deployment of control systems with network-connected components has made feedback control systems vulnerable to attacks over the network. This paper considers the problem of intrusion detection and mitigation in supervisory control…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
Assistive technologies increasingly support independence, accessibility, and safety for older adults, people with disabilities, and individuals requiring continuous care. Two major categories are virtual assistive systems and robotic…
The reliance of Large Language Models and Internet of Things systems on massive, globally distributed data flows creates systemic security and privacy challenges. When data traverses borders, it becomes subject to conflicting legal regimes,…
Concerns around future dangers from advanced AI often centre on systems hypothesised to have intrinsic characteristics such as agent-like behaviour, strategic awareness, and long-range planning. We label this cluster of characteristics as…
Protecting digital identities of human face from various attack vectors is paramount, and face anti-spoofing plays a crucial role in this endeavor. Current approaches primarily focus on detecting spoofing attempts within individual frames…
With the rapid diffusion of social networks in combination with mobile phones, a new social threat of sextortion has emerged, in which vulnerable young women are essentially blackmailed with their explicit shared multimedia content. The…
In a nutshell, "the cloud" refers to a collection of interconnected computing resources made possible by an extensive, real-time communication network like the internet. Because of its potential to reduce processing costs, the emerging…
Internet-of-things (IoT) is perpetually revolutionizing our daily life and rapidly transforming physical objects into an ubiquitous connected ecosystem. Due to their massive deployment and moderate security levels, those devices face a lot…
As AI capabilities advance rapidly, flexible hardware-enabled guarantees (flexHEGs) offer opportunities to address international security challenges through comprehensive governance frameworks. This report examines how flexHEGs could enable…
Organisations are rapidly adopting artificial intelligence (AI) tools to perform tasks previously undertaken by people. The potential benefits are enormous. Separately, some organisations deploy personnel security measures to mitigate the…
In an era where the Internet of Things (IoT) intersects increasingly with generative Artificial Intelligence (AI), this article scrutinizes the emergent security risks inherent in this integration. We explore how generative AI drives…