相关论文: Learning Contextual Runtime Monitors for Safe AI-B…

Traditional AI safety evaluations on isolated LLMs are insufficient as multi-agent AI ensembles become prevalent, introducing novel emergent risks. This paper introduces the Multi-Agent Emergent Behavior Evaluation (MAEBE) framework to…

Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed context vectors, little is known about the case of…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…

This paper presents an auto-optimal model predictive control (MPC) framework enhanced with active learning, designed to autonomously track optimal operational conditions in an unknown environment,where the conditions may dynamically adjust…

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…

From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations. For this reason, there has been a growing interest in the anomaly detection (AD) task. Since we cannot…

In machine learning, the one-class classification problem occurs when training instances are only available from one class. It has been observed that making use of this class's structure, or its different contexts, may improve one-class…

The interest in using reinforcement learning (RL) controllers in safety-critical applications such as robot navigation around pedestrians motivates the development of additional safety mechanisms. Running RL-enabled systems among uncertain…

Learning has propelled the cutting edge of performance in robotic control to new heights, allowing robots to operate with high performance in conditions that were previously unimaginable. The majority of the work, however, assumes that the…

Anomaly detection aims to identify observations that deviate from expected behavior. Because anomalous events are inherently sparse, most frameworks are trained exclusively on normal data to learn a single reference model of normality. This…

In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers…

Ensuring that critical IoT systems function safely and smoothly depends a lot on finding anomalies quickly. As more complex systems, like smart healthcare, energy grids and industrial automation, appear, it is easier to see the shortcomings…

Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these…

Ensuring safety in autonomous driving requires precise, real-time risk assessment and adaptive behavior. Prior work on risk estimation either outputs coarse, global scene-level metrics lacking interpretability, proposes indicators without…

There is a growing demand for mobile robots to operate in more variable environments, where guaranteeing safe robot navigation is a priority, in addition to time performance. To achieve this, current solutions for local planning use a…

Artificial intelligence (AI) and reinforcement learning (RL) have shown significant promise in wireless systems, enabling dynamic spectrum allocation, traffic management, and large-scale Internet of Things (IoT) coordination. However, their…

Modern digital applications extensively integrate Artificial Intelligence models into their core systems, offering significant advantages for automated decision-making. However, these AI-based systems encounter reliability and safety…

Autonomous UAV infiltration in dynamic contested environments remains a significant challenge due to the partially observable nature of threats and the conflicting objectives of mission efficiency versus survivability. Traditional…

Automatic Modulation Classification (AMC) is critical for efficient spectrum management and robust wireless communications. However, AMC remains challenging due to the complex interplay of signal interference and noise. In this work, we…