Related papers: ABIGX: A Unified Framework for eXplainable Fault D…

Lane detection stands as a crucial perception task in autonomous driving and advanced driver assistance systems. However, existing methods still degrade in complex real scenarios due to two major limitations. First, classification…

State-of-the-art machine learning models are routinely trained on large-scale distributed clusters. Crucially, such systems can be compromised when some of the computing devices exhibit abnormal (Byzantine) behavior and return arbitrary…

The ambiguity function is fundamental to radar waveform design, characterizing range and Doppler resolution capabilities. However, its traditional formulation involves non-differentiable operations, preventing integration with…

We propose a possible solution to a public challenge posed by the Fair Isaac Corporation (FICO), which is to provide an explainable model for credit risk assessment. Rather than present a black box model and explain it afterwards, we…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Deep Learning systems (DL) based on Deep Neural Networks (DNNs) are more and more used in various aspects of our life, including unmanned vehicles, speech processing, and robotics. However, due to the limited dataset and the dependence on…

In traditional federated learning, a single global model cannot perform equally well for all clients. Therefore, the need to achieve the client-level fairness in federated system has been emphasized, which can be realized by modifying the…

Novel AI-based arc fault diagnosis models have demonstrated outstanding performance in terms of classification accuracy. However, an inherent problem is whether these models can actually be trusted to find arc faults. In this light, this…

In many applications, gradient evaluations are inherently approximate, motivating the development of optimization methods that remain reliable under inexact first-order information. A common strategy in this context is adaptive evaluation,…

Debugging is one of the most time-consuming and expensive tasks in software development and circuit design. Several formula-based fault localisation (FBFL) methods have been proposed, but they fail to guarantee a set of diagnoses across all…

This letter presents a novel approach in the field of Active Fault Detection (AFD), by explicitly separating the task into two parts: Passive Fault Detection (PFD) and control input design. This formulation is very general, and most…

Constrained image splicing detection and localization (CISDL) is a newly proposed challenging task for image forensics, which investigates two input suspected images and identifies whether one image has suspected regions pasted from the…

A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly scores over reconstruction loss of input. Due to the rare occurrence of anomalies, optimizing such networks can be a cumbersome…

The explanation to an AI model's prediction used to support decision making in cyber security, is of critical importance. It is especially so when the model's incorrect prediction can lead to severe damages or even losses to lives and…

Industrial anomaly detection is a challenging open-set task that aims to identify unknown anomalous patterns deviating from normal data distribution. To avoid the significant memory consumption and limited generalizability brought by…

Despite the growing popularity of modern machine learning techniques (e.g. Deep Neural Networks) in cyber-security applications, most of these models are perceived as a black-box for the user. Adversarial machine learning offers an approach…

Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliable. Many assessments rely on mismatched models, unverified…

As machine learning models are increasingly deployed in sensitive application areas, the demand for interpretable and trustworthy decision-making has increased. Random Forests (RF), despite their widespread use and strong performance on…

We present FACADE, a novel probabilistic and geometric framework designed for unsupervised mechanistic anomaly detection in deep neural networks. Its primary goal is advancing the understanding and mitigation of adversarial attacks. FACADE…

In this paper, we introduce a novel task termed unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly…