相关论文: Towards Interdependent Safety Security Assessments…
When deployed in the real world, safe control methods must be robust to unstructured uncertainties such as modeling error and external disturbances. Typical robust safety methods achieve their guarantees by always assuming that the…
Mixnets provide strong meta-data privacy and recent academic research and industrial projects have made strides in making them more secure, performance, and scalable. In this paper, we focus our work on stratified Mixnets -- a popular…
In 2023, the National Eating Disorders Association's (NEDA) chatbot Tessa was suspended after providing harmful weight-loss advice to vulnerable users-an avoidable failure that underscores the risks of unsafe AI in healthcare contexts. This…
Integrated safety and security assurance for complex systems is difficult for many technical and socio-technical reasons such as mismatched processes, inadequate information, differing use of language and philosophies, etc.. Many…
Security situational awareness refers to identifying, mitigating, and preventing digital cyber threats by gathering information to understand the current situation. With awareness, the basis for decisions is present, particularly in complex…
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…
Power system operators need tools for rapid, real-time counterfactual assessments of grid security under fast-changing conditions. Traditional N-1 contingency analysis lacks dynamic evaluation, especially of frequency swings from common…
Releasing connection data from social networking services can pose a significant threat to user privacy. In our work, we consider structural social network de-anonymization attacks, which are used when a malicious party uses connections in…
Safety assurance is of paramount importance across various domains, including automotive, aerospace, and nuclear energy, where the reliability and acceptability of mission-critical systems are imperative. This assurance is effectively…
Testing and evaluation is an important step before the large-scale application of the autonomous driving systems (ADSs). Based on the three level of scenario abstraction theory, a testing can be performed within a logical scenario, followed…
In recent years, there has been a shift in computing architectures, moving away from centralized cloud computing towards decentralized edge and fog computing. This shift is driven by factors such as the increasing volume of data generated…
This paper addresses a method to analyze the covert social network foundation hidden behind the terrorism disaster. It is to solve a node discovery problem, which means to discover a node, which functions relevantly in a social network, but…
As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…
Road crashes remain a leading cause of preventable fatalities. Existing prediction models predominantly produce binary outcomes, which offer limited actionable insights for real-time driver feedback. These approaches often lack continuous…
In recent years, cyberattacks - along with physical faults - have become an increasing factor causing system failures, especially in DER (Distributed Energy Resources) systems. In addition, according to the literature, a number of faults…
Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…
Due to their interesting features, blockchains have become popular in recent years. They are full-stack systems where security is a critical factor for their success. The main focus of this work is to systematize knowledge about security…
This work develops a robust adaptive control strategy for discrete-time systems using Control Barrier Functions (CBFs) to ensure safety under parametric model uncertainty and disturbances. A key contribution of this work is establishing a…
As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…
Recognizing, assessing, countering, and mitigating the biases of different nature from heterogeneous sources is a critical problem in designing a cognitive Decision Support System (DSS). An example of such a system is a cognitive…