Related papers: A Novel Contrastive Loss for Zero-Day Network Intr…

In the last decades, researchers, practitioners and companies struggled in devising mechanisms to detect malicious activities originating security threats. Amongst the many solutions, network intrusion detection emerged as one of the most…

Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples…

The primary objective of methods in continual learning is to learn tasks in a sequential manner over time (sometimes from a stream of data), while mitigating the detrimental phenomenon of catastrophic forgetting. This paper proposes a…

Machine learning models deployed in the wild naturally encounter unlabeled samples from both known and novel classes. Challenges arise in learning from both the labeled and unlabeled data, in an open-world semi-supervised manner. In this…

Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are self-trained. Existing contrastive learning methods either…

Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

Despite significant progress in Anomaly Detection (AD), the robustness of existing detection methods against adversarial attacks remains a challenge, compromising their reliability in critical real-world applications such as autonomous…

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…

Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly…

Recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this letter, we propose a novel method to detect adversarial inputs, by augmenting the…

Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…

The problem of detecting data anomaly is considered. Under the null hypothesis that models anomaly-free data, measurements are assumed to be from an unknown distribution with some authenticated historical samples. Under the composite…

Contrastive learning relies on an assumption that positive pairs contain related views, e.g., patches of an image or co-occurring multimodal signals of a video, that share certain underlying information about an instance. But what if this…

Distracted driving is one of the major reasons for vehicle accidents. Therefore, detecting distracted driving behaviors is of paramount importance to reduce the millions of deaths and injuries occurring worldwide. Distracted or anomalous…

Ransomware has become a critical threat to cybersecurity due to its rapid evolution, the necessity for early detection, and growing diversity, posing significant challenges to traditional detection methods. While AI-based approaches had…

Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both gradient-based and distribution shift threat models. Existing defenses typically apply…

Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…