Related papers: Access Controls Will Solve the Dual-Use Dilemma
Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…
Accessibility forums and, more recently, generative AI tools have become vital resources for blind users seeking solutions to computer-interaction issues and learning about new assistive technologies, screen reader features, tutorials, and…
Cheating is a real problem in the Internet of Things. The fundamental question that needs to be answered is how we can trust the validity of the data being generated in the first place. The problem, however, isn't inherent in whether or not…
Advanced AI systems may be developed which exhibit capabilities that present significant risks to public safety or security. They may also exhibit capabilities that may be applied defensively in a wide set of domains, including (but not…
As AI systems are integrated into high stakes social domains, researchers now examine how to design and operate them in a safe and ethical manner. However, the criteria for identifying and diagnosing safety risks in complex social contexts…
Semantic Web is an open, distributed, and dynamic environment where access to resources cannot be controlled in a safe manner unless the access decision takes into account during discovery of web services. Security becomes the crucial…
Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent activities, violate human rights, create harmful fake images,…
We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse…
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…
Regulatory frameworks for the use of AI are emerging. However, they trail behind the fast-evolving malicious AI technologies that can quickly cause lasting societal damage. In response, we introduce a pioneering Assistive AI framework…
In today's society, where Artificial Intelligence (AI) has gained a vital role, concerns regarding user's trust have garnered significant attention. The use of AI systems in high-risk domains have often led users to either under-trust it,…
This paper explores the role and challenges of Artificial Intelligence (AI) algorithms, specifically AI-based software elements, in autonomous driving systems. These AI systems are fundamental in executing real-time critical functions in…
Artificial Intelligence (AI) has become an important part of our everyday lives, yet user requirements for designing AI-assisted systems in law enforcement remain unclear. To address this gap, we conducted qualitative research on…
Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…
AI-based systems can increasingly perform work tasks autonomously. In safety-critical tasks, human oversight of these systems is required to mitigate risks and to ensure responsibility in case something goes wrong. Since people often…
As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from…
Artificial intelligence (AI) model creators commonly attach restrictive terms of use to both their models and their outputs. These terms typically prohibit activities ranging from creating competing AI models to spreading disinformation.…
Safety frameworks have emerged as a best practice for managing risks from frontier artificial intelligence (AI) systems. However, it may be difficult for stakeholders to know if companies are adhering to their frameworks. This paper…
Open access to publication, software and hardware is central to robotics: it lowers barriers to entry, supports reproducible science and accelerates reliable system development. However, openness also exacerbates the inherent dual-use risks…
The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security. Although the two disciplines now come…