Related papers: Automatic ISA analysis for Secure Context Switchin…
Cyber risk assessment is a fundamental activity for enhancing the protection of an organization, identifying and evaluating the exposure to cyber threats. Currently, this activity is carried out mainly manually and the identification and…
When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…
Many sequential decision problems involve finding a policy that maximizes total reward while obeying safety constraints. Although much recent research has focused on the development of safe reinforcement learning (RL) algorithms that…
Multimedia Information security becomes a important part for the organization's intangible assets. Level of confidence and stakeholder trusted are performance indicator as successes organization, it is imperative for organizations to use…
We systematically evaluate the quality of widely used adversarial safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world adversarial attacks based on three…
Target Safety Assessment (TSA) requires systematic integration of heterogeneous evidence, including genetic, transcriptomic, target homology, pharmacological, and clinical data, to evaluate potential safety liabilities of therapeutic…
Modern enterprises increasingly adopt diverse technology stacks with various programming languages, posing significant challenges for static application security testing (SAST). Existing taint analysis tools are predominantly designed for…
The deployment of Socially Intelligent Agents (SIAs) in learning environments has proven to have several advantages in different areas of application. Social Agent Authoring Tools allow scenario designers to create tailored experiences with…
This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…
A new LISA simulator (LISACode) is presented. Its ambition is to achieve a new degree of sophistication allowing to map, as closely as possible, the impact of the different sub-systems on the measurements. LISACode is not a detailed…
Shared autonomy holds promise for improving the usability and accessibility of assistive robotic arms, but current methods often rely on costly expert demonstrations and remain static after pretraining, limiting their ability to handle…
We present a formalization of modern SAT solvers and their properties in a form of abstract state transition systems. SAT solving procedures are described as transition relations over states that represent the values of the solver's global…
In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variation. We propose SAIL, a framework that reframes robot imitation as an iterative…
In large programming classes, it takes a significant effort from teachers to evaluate exercises and provide detailed feedback. In systems programming, test cases are not sufficient to assess exercises, since concurrency and resource…
Exploration algorithms for explicit-state transition systems are a core back-end technology in program verification. They can be applied to programs by generating the transition system on the fly, avoiding an expensive up-front translation.…
Software tends to be highly configurable, but most applications are hardly context aware. For example, a web browser provides many settings to configure printers and proxies, but nevertheless it is unable to dynamically adapt to a new…
A major concern amongst AI safety practitioners is the possibility of loss of control, whereby humans lose the ability to exert control over increasingly advanced AI systems. The range of concerns is wide, spanning current day risks to…
Marine vessel re-identification technology is an important component of intelligent shipping systems and an important part of the visual perception tasks required for marine surveillance. However, unlike the situation on land, the maritime…
As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…
Context: Static Application Security Testing Tools (SASTTs) identify software vulnerabilities to support the security and reliability of software applications. Interestingly, several studies have suggested that alternative solutions may be…