Related papers: Access Controls Will Solve the Dual-Use Dilemma
The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Many people struggle to control their use of digital devices. However, our understanding of the design mechanisms that support user self-control remains limited. In this paper, we make two contributions to HCI research in this space: first,…
AI is transforming life sciences research at unprecedented speed, accelerating discovery across protein structure prediction, genome modeling, and drug development (Jumper et al., 2021; Mak et al., 2024). Yet this rapid advancement, coupled…
Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations, yet ignores uncertainty reduction and leads to overly conservative behavior. Actively…
The digital age requires strong security measures to protect online activities. Two-Factor Authentication (2FA) has emerged as a critical solution. However, its implementation presents significant challenges, particularly in terms of…
When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this…
Assuring safety of artificial intelligence (AI) applied to safety-critical systems is of paramount importance. Especially since research in the field of automated driving shows that AI is able to outperform classical approaches, to handle…
What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on…
Alphanumeric authentication routinely fails to regulate access to resources with the required stringency, primarily due to usability issues. Initial deployment did not reveal the problems of passwords, deep and profound flaws only emerged…
Systems that augment sensory abilities are increasingly employing AI and machine learning (ML) approaches, with applications ranging from object recognition and scene description tools for blind users to sound awareness tools for d/Deaf…
This paper examines the dual-use challenges of foundation models and the consequent risks they pose for international security. As artificial intelligence (AI) models are increasingly tested and deployed across both civilian and military…
Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, these decisions are made by users during app installation or at runtime. However, due to the…
Recent research advances in Artificial Intelligence (AI) have yielded promising results for automated software vulnerability management. AI-based models are reported to greatly outperform traditional static analysis tools, indicating a…
Potential malicious misuse of civilian artificial intelligence (AI) poses serious threats to security on a national and international level. Besides defining autonomous systems from a technological viewpoint and explaining how AI…
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…
Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can…
Access control policies are used to restrict access to sensitive records for authorized users only. One approach for specifying policies is using role based access control (RBAC) where authorization is given to roles instead of users. Users…
Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…
Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations, yet ignores uncertainty reduction and leads to overly conservative behavior. Actively…