相关论文: Targeted Attack on Deep RL-based Autonomous Drivin…

Deep learning models are vulnerable to adversarial examples, which can fool a target classifier by imposing imperceptible perturbations onto natural examples. In this work, we consider the practical and challenging decision-based black-box…

In this paper, we study how to secure the platooning of autonomous vehicles when an unknown vehicle is under attack and bounded system uncertainties exist. For the attacked vehicle, its position and speed measurements from GPS can be…

Robotics has proved to be an indispensable tool in many industrial as well as social applications, such as warehouse automation, manufacturing, disaster robotics, etc. In most of these scenarios, damage to the agent while accomplishing…

AI-based defensive solutions are necessary to defend networks and information assets against intelligent automated attacks. Gathering enough realistic data for training machine learning-based defenses is a significant practical challenge.…

Autonomous systems such as self-driving cars and general-purpose robots are safety-critical systems that operate in highly uncertain and dynamic environments. We propose an interactive multi-agent framework where the system-under-design is…

Deep reinforcement learning methods have been widely used in recent years for autonomous vehicle's decision-making. A key issue is that deep neural networks can be fragile to adversarial attacks or other unseen inputs. In this paper, we…

Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully…

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

Autonomous vehicles (AVs) face significant threats to their safe operation in complex traffic environments. Adversarial training has emerged as an effective method of enabling AVs to preemptively fortify their robustness against malicious…

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large literature has studied the case of test-time attacks on…

Deep Reinforcement Learning (RL) has shown remarkable success in robotics with complex and heterogeneous dynamics. However, its vulnerability to unknown disturbances and adversarial attacks remains a significant challenge. In this paper, we…

Autonomous inspection in hazardous environments requires AI agents that can interpret high-level goals and execute precise control. A key capability for such agents is spatial grounding, for example when a drone must center a detected…

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP…

Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the…

Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models. However, in such visual perception pipeline the detected objects…

Machine Learning applications are acknowledged at the foundation of autonomous driving, because they are the enabling technology for most driving tasks. However, the inclusion of trained agents in automotive systems exposes the vehicle to…

Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under uncertainty. By integrating deep neural networks (DNNs) into the RL framework, deep reinforcement…