相关论文: AdvDO: Realistic Adversarial Attacks for Trajector…

Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that…

Machine learning has witnessed tremendous growth in its adoption and advancement in the last decade. The evolution of machine learning from traditional algorithms to modern deep learning architectures has shaped the way today's technology…

Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…

Autonomous vehicles (AVs) rely on complex perception and communication systems, making them vulnerable to adversarial attacks that can compromise safety. While simulation offers a scalable and safe environment for robustness testing,…

Designing effective defense against adversarial attacks is a crucial topic as deep neural networks have been proliferated rapidly in many security-critical domains such as malware detection and self-driving cars. Conventional defense…

While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…

Despite advancements in perception and planning for autonomous vehicles (AVs), validating their performance remains a significant challenge. The deployment of planning algorithms in real-world environments is often ineffective due to…

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Predicting the behaviour (i.e., manoeuvre/trajectory) of other road users, including vehicles, is critical for the safe and efficient operation of autonomous vehicles (AVs), a.k.a., automated driving systems (ADSs). Due to the uncertain…

The rapid development of artificial intelligence, especially deep learning technology, has advanced autonomous driving systems (ADSs) by providing precise control decisions to counterpart almost any driving event, spanning from anti-fatigue…

Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…

As highly automated vehicles reach higher deployment rates, they find themselves in increasingly dangerous situations. Knowing that the consequence of a crash is significant for the health of occupants, bystanders, and properties, as well…

Existing approaches in reinforcement learning train an agent to learn desired optimal behavior in an environment with rule based surrounding agents. In safety critical applications such as autonomous driving it is crucial that the rule…

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…

With the rapid development of Artificial Intelligence (AI), the problem of AI security has gradually emerged. Most existing machine learning algorithms may be attacked by adversarial examples. An adversarial example is a slightly modified…

Accurate and robust trajectory predictions of road users are needed to enable safe automated driving. To do this, machine learning models are often used, which can show erratic behavior when presented with previously unseen inputs. In this…

Stand-alone Visual Place Recognition (VPR) systems have little defence against a well-designed adversarial attack, which can lead to disastrous consequences when deployed for robot navigation. This paper extensively analyzes the effect of…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

Visual tracking is adopted to extensive unmanned aerial vehicle (UAV)-related applications, which leads to a highly demanding requirement on the robustness of UAV trackers. However, adding imperceptible perturbations can easily fool the…

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…