Related papers: A Distance-based Anomaly Detection Framework for D…

Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However, like any other software system, DRL-based software systems are susceptible to faults that pose…

Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied. In this paper, we show that existing metric…

We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control into a perception module and a controller module, we can train…

Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data. Most existing AD studies assume that the training and test data are drawn…

We can often verify the correctness of neural network outputs using ground truth labels, but we cannot reliably determine whether the output was produced by normal or anomalous internal mechanisms. Mechanistic anomaly detection (MAD) aims…

Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. Yet, it poses a critical challenge since the scheduler needs to make real-time…

We introduce Dynamic Distinction Learning (DDL) for Video Anomaly Detection, a novel video anomaly detection methodology that combines pseudo-anomalies, dynamic anomaly weighting, and a distinction loss function to improve detection…

As the horizon of intelligent transportation expands with the evolution of Automated Driving Systems (ADS), ensuring paramount safety becomes more imperative than ever. Traditional risk assessment methodologies, primarily crafted for…

Differentiable environments have heralded new possibilities for learning control policies by offering rich differentiable information that facilitates gradient-based methods. In comparison to prevailing model-free reinforcement learning…

Deep reinforcement learning (DRL) has proven extremely useful in a large variety of application domains. However, even successful DRL-based software can exhibit highly undesirable behavior. This is due to DRL training being based on…

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection in such critical infrastructures. This…

Anomaly detection in complex, high-dimensional data, such as UAV sensor readings, is essential for operational safety but challenging for existing methods due to their limited sensitivity, scalability, and inability to capture intricate…

Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…

We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach…

Forecasting multivariate hidden Markov processes is challenging due to nonlinear and nonstationary observations, latent state transitions, and cross-sequence dependencies. While deep learning methods achieve strong predictive accuracy, they…

Learning in MDPs with highly complex state representations is currently possible due to multiple advancements in reinforcement learning algorithm design. However, this incline in complexity, and furthermore the increase in the dimensions of…

Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle, imperceptible perturbations that can lead to incorrect predictions. While detection-based defenses offer a practical alternative to adversarial training,…

Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness and reliability of machine learning systems deployed in real-world applications. Recent approaches have explored the use of unlabeled data, showing…

The significance of vehicle-to-everything (V2X) communications has been ever increased as connected and autonomous vehicles get more emergent in practice. The key challenge is the dynamicity: each vehicle needs to recognize the frequent…

Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the…