Related papers: Adversarial Body Shape Search for Legged Robots
We address adversarial attacks on the actuators at the joints of legged robots trained by deep reinforcement learning. The vulnerability to the joint attacks can significantly impact the safety and robustness of legged robots. In this…
Skeleton-based action recognition models have recently been shown to be vulnerable to adversarial attacks. Compared to adversarial attacks on images, perturbations to skeletons are typically bounded to a lower dimension of approximately 100…
Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted inputs that are designed…
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching adversarial patches to real objects. However, most of the existing…
Humanoid robots are expected to operate reliably over long horizons while executing versatile whole-body skills. Yet Reinforcement Learning (RL) motion policies typically lose stability under prolonged operation, sensor/actuator noise, and…
Due to their performance and simplicity, rigid body simulators are often used in applications where the objects of interest can considered very stiff. However, no material has infinite stiffness, which means there are potentially cases…
Adversarial attack on skeletal motion is a hot topic. However, existing researches only consider part of dynamic features when measuring distance between skeleton graph sequences, which results in poor imperceptibility. To this end, we…
Adversarial attacks on robotic grasping provide valuable insights into evaluating and improving the robustness of these systems. Unlike studies that focus solely on neural network predictions while overlooking the physical principles of…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…
With the trend of adversarial attacks, researchers attempt to fool trained object detectors in 2D scenes. Among many of them, an intriguing new form of attack with potential real-world usage is to append adversarial patches (e.g. logos) to…
Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…
Human motion prediction has achieved a brilliant performance with the help of convolution-based neural networks. However, currently, there is no work evaluating the potential risk in human motion prediction when facing adversarial attacks.…
As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…
Neural networks are prone to misclassify slightly modified input images. Recently, many defences have been proposed, but none have improved the robustness of neural networks consistently. Here, we propose to use adversarial attacks as a…
Over the past decade, deep learning has revolutionized conventional tasks that rely on hand-craft feature extraction with its strong feature learning capability, leading to substantial enhancements in traditional tasks. However, deep neural…
Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object detection, these models remain susceptible to…
In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods against adversarial…
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…
The paper develops a new adversarial attack against deep neural networks (DNN), based on applying bio-inspired design to moving physical objects. To the best of our knowledge, this is the first work to introduce physical attacks with a…