Related papers: GAN-Based Single-Stage Defense for Traffic Sign Cl…
The anonymous nature of darknets is commonly exploited for illegal activities. Previous research has employed machine learning and deep learning techniques to automate the detection of darknet traffic in an attempt to block these criminal…
Many adversarial attacks on autonomous-driving perception models fail to cause system-level failures once deployed in a full driving stack. The main reason for such ineffectiveness is that once deployed in a system (e.g., within a…
We propose a novel GAN training scheme that can handle any level of labeling in a unified manner. Our scheme introduces a form of artificial labeling that can incorporate manually defined labels, when available, and induce an alignment…
Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show…
Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics should be chosen so as to capture the downstream impact of…
In recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To…
LiDAR-based segmentation is essential for reliable perception in autonomous vehicles, yet modern segmentation networks are highly susceptible to adversarial attacks that can compromise safety. Most existing defenses are designed for…
Adversarial attacks in the physical world pose a significant threat to the security of vision-based systems, such as facial recognition and autonomous driving. Existing adversarial patch methods primarily focus on improving attack…
In recent years, visual tracking methods based on convolutional neural networks and Transformers have achieved remarkable performance and have been successfully applied in fields such as autonomous driving. However, the numerous security…
Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving (AD) systems. However, these methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this…
Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…
We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a…
With the rapid development of deep learning, object detectors have demonstrated impressive performance; however, vulnerabilities still exist in certain scenarios. Current research exploring the vulnerabilities using adversarial patches…
Generative Adversarial Networks (GAN) are trained to generate sample images of interest distribution. To this end, generator network of GAN learns implicit distribution of real data set from the classification with candidate generated…
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple…
One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…
Object detection plays a crucial role in many security-sensitive applications. However, several recent studies have shown that object detectors can be easily fooled by physically realizable attacks, \eg, adversarial patches and recent…
Adversarial patches pose a realistic threat model for physical world attacks on autonomous systems via their perception component. Autonomous systems in safety-critical domains such as automated driving should thus contain a fail-safe…
Object detection techniques for Unmanned Aerial Vehicles (UAVs) rely on Deep Neural Networks (DNNs), which are vulnerable to adversarial attacks. Nonetheless, adversarial patches generated by existing algorithms in the UAV domain pay very…
Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep…