Related papers: Preliminary Investigation into Uncertainty-Aware A…

The techniques used in modern attacks have become an important factor for investigation. As we advance further into the digital age, cyber attackers are employing increasingly sophisticated and highly threatening methods. These attacks…

Evidential Deep Learning (EDL) has emerged as an efficient, sampling-free strategy for uncertainty estimation. A series of EDL variants have been proposed to address specific limitations of the original framework, achieving notable success.…

Advanced persistent threat (APT) is widely acknowledged to be the most sophisticated and potent class of security threat. APT refers to knowledgeable human attackers that are organized, highly sophisticated and motivated to achieve their…

Advanced Persistent Threats (APTs) pose a significant security risk to organizations and industries. These attacks often lead to severe data breaches and compromise the system for a long time. Mitigating these sophisticated attacks is…

Despite the robust security features inherent in the 5G framework, attackers will still discover ways to disrupt 5G unmanned aerial vehicle (UAV) operations and decrease UAV control communication performance in Air-to-Ground (A2G) links.…

Advanced Persistent Threat (APT) attacks are highly sophisticated and employ a multitude of advanced methods and techniques to target organizations and steal sensitive and confidential information. APT attacks consist of multiple stages and…

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty.…

The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution moreover correlates with a model's epistemic uncertainty,…

This work reveals an evidential signal that emerges from the uncertainty value in Evidential Deep Learning (EDL). EDL is one example of a class of uncertainty-aware deep learning approaches designed to provide confidence (or epistemic…

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian…

Advanced Persistent Threats (APTs) pose a severe challenge to cyber defense due to their stealthy behavior and the extreme class imbalance inherent in detection datasets. To address these issues, we propose a novel active learning-based…

Advanced persistent threats (APTs) are stealthy attacks which make use of social engineering and deception to give adversaries insider access to networked systems. Against APTs, active defense technologies aim to create and exploit…

Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world…

Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step…

Advanced persistent threats (APTs) are organized prolonged cyberattacks by sophisticated attackers. Although APT activities are stealthy, they interact with the system components and these interactions lead to information flows. Dynamic…

We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\textit{Calibrated Evidential…

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing…

Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in…

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs). This limitation is one of the key challenges in the adoption of DNNs in high-assurance systems such as…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…