相关论文: Formal Modeling and SMT-Based Parameterized Verifi…

The control design tools for linear systems typically involves pole placement and computing Lyapunov functions which are useful for ensuring stability. But given higher requirements on control design, a designer is expected to satisfy other…

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this…

Despite the prevalence of images and texts in machine learning, tabular data remains widely used across various domains. Existing deep learning models, such as convolutional neural networks and transformers, perform well however demand…

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed…

Recent learning-based safety filters have outperformed conventional methods, such as hand-crafted Control Barrier Functions (CBFs), by effectively adapting to complex constraints. However, these learning-based approaches lack formal safety…

The work concerns formal verification of workflow-oriented software models using deductive approach. The formal correctness of a model's behaviour is considered. Manually building logical specifications, which are considered as a set of…

This paper introduces reviewability as a framework for improving the accountability of automated and algorithmic decision-making (ADM) involving machine learning. We draw on an understanding of ADM as a socio-technical process involving…

Model-based safety assessment has been one of the leading research thrusts of the System Safety Engineering community for over two decades. However, there is still a lack of consensus on what MBSA is. The ambiguity in the identity of MBSA…

Markov Decision Processes (MDPs) are a classical model for decision making in the presence of uncertainty. Often they are viewed as state transformers with planning objectives defined with respect to paths over MDP states. An increasingly…

Model-based mutation testing uses altered test models to derive test cases that are able to reveal whether a modelled fault has been implemented. This requires conformance checking between the original and the mutated model. This paper…

The problem of damage detection and identification is of interest for many aerospace and aeronautical engineering systems. However, relevant literature mostly focuses on subsystems and parts, rather than full airframes. In structural…

Trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods…

JBMC is an open-source SAT- and SMT-based bounded model checking tool for verifying Java bytecode. JBMC relies on an operational model of the Java libraries, which conservatively approximates their semantics, to verify assertion violations,…

Realm Management Monitor (RMM) is an essential firmware component within the recent Arm Confidential Computing Architecture (Arm CCA). Previous work applies formal techniques to verify the specification and prototype reference…

Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to…

We study the extension of relational multiagent systems (RMASs), where agents manipulate full-fledged relational databases, with data types and facets equipped with domain-specific, rigid relations (such as total orders). Specifically, we…

Accurate and rapid structural damage assessment (SDA) is crucial for post-disaster management, helping responders prioritise resources, plan rescues, and support recovery. Traditional field inspections, though precise, are limited by…

Machine unlearning aims to unlearn data points from a learned model, offering a principled way to process data-deletion requests and mitigate privacy risks without full retraining. Prior work has mainly studied unsupervised / supervised…

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment…

Upcoming certification actions related to the security of machine learning (ML) based systems raise major evaluation challenges that are amplified by the large-scale deployment of models in many hardware platforms. Until recently, most of…