相关论文: First Step Towards EXPLAINable DGA Multiclass Clas…

Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios.…

For a long time, malware classification and analysis have been an arms-race between antivirus systems and malware authors. Though static analysis is vulnerable to evasion techniques, it is still popular as the first line of defense in…

In some problem spaces, the high cost of obtaining ground truth labels necessitates use of lower quality reference datasets. It is difficult to benchmark model performance using these datasets, as evaluation results may be biased. We…

Generative Adversarial Networks (GANs) are notoriously difficult to train especially for complex distributions and with limited data. This has driven the need for tools to audit trained networks in human intelligible format, for example, to…

Artificial Intelligence (AI) has become an integral part of modern-day security solutions for its ability to learn very complex functions and handling "Big Data". However, the lack of explainability and interpretability of successful AI…

An important step towards explaining deep image classifiers lies in the identification of image regions that contribute to individual class scores in the model's output. However, doing this accurately is a difficult task due to the…

Probabilistic graphical modeling (PGM) provides a framework for formulating an interpretable generative process of data and expressing uncertainty about unknowns, but it lacks flexibility. Deep learning (DL) is an alternative framework for…

State-of-the-art deep learning (DL)-based network intrusion detection systems (NIDSs) offer limited "explainability". For example, how do they make their decisions? Do they suffer from hidden correlations? Prior works have applied…

This paper addresses the domain generalization (DG) problem in deep learning. While most DG methods focus on enforcing visual feature invariance, we leverage the reasoning capability of multimodal large language models (MLLMs) and explore…

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data in a source domain. Most deep UDA approaches operate in a…

Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more accurate and contextually rich responses. To improve the…

While contemporary deep learning malware detectors define a dominant defense paradigm, their sophistication also exposes them to novel structural evasion attacks, a limitation we attribute to their inherent inability to express epistemic…

The new era of image segmentation leveraging the power of Deep Neural Nets (DNNs) comes with a price tag: to train a neural network for pixel-wise segmentation, a large amount of training samples has to be manually labeled on…

For deep learning applications, the massive data development (e.g., collecting, labeling), which is an essential process in building practical applications, still incurs seriously high costs. In this work, we propose an effective data…

Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution. To overcome this problem, domain generalisation (DG) methods aim to…

Botnets and malware continue to avoid detection by static rules engines when using domain generation algorithms (DGAs) for callouts to unique, dynamically generated web addresses. Common DGA detection techniques fail to reliably detect DGA…

Domain generalization (DG) attempts to generalize a model trained on single or multiple source domains to the unseen target domain. Benefiting from the success of Visual-and-Language Pre-trained models in recent years, we argue that it is…

Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features…

This work generalizes the problem of unsupervised domain generalization to the case in which no labeled samples are available (completely unsupervised). We are given unlabeled samples from multiple source domains, and we aim to learn a…