Related papers: BadFusion: 2D-Oriented Backdoor Attacks against 3D…

Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented…

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. Existing backdoor…

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Although multiple fusion approaches have been proposed, they can be classified into either sparse-only or dense-only fashion based…

Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current Lidar sensors still lag two decades behind traditional color cameras in terms of resolution and cost. For autonomous driving, this means that large…

Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore backdoor attack…

Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

3D object detection serves as the core basis of the perception tasks in autonomous driving. Recent years have seen the rapid progress of multi-modal fusion strategies for more robust and accurate 3D object detection. However, current…

Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and…

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings…

This paper presents a novel indoor layout estimation system based on the fusion of 2D LiDAR and intensity camera data. A ground robot explores an indoor space with a single floor and vertical walls, and collects a sequence of intensity…

Modern autonomous driving (AD) systems leverage 3D object detection to perceive foreground objects in 3D environments for subsequent prediction and planning. Visual 3D detection based on RGB cameras provides a cost-effective solution…

Today's state-of-the-art methods for 3D object detection are based on lidar, stereo, or monocular cameras. Lidar-based methods achieve the best accuracy, but have a large footprint, high cost, and mechanically-limited angular sampling…

Face Recognition Systems that operate in unconstrained environments capture images under varying conditions,such as inconsistent lighting, or diverse face poses. These challenges require including a Face Detection module that regresses…

In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior…

Deep learning models have been shown to be susceptible to adversarial attacks with visually imperceptible perturbations. Even this poses a serious security challenge for the localization of self-driving cars, there has been very little…

Most autonomous vehicles (AVs) rely on LiDAR and RGB camera sensors for perception. Using these point cloud and image data, perception models based on deep neural nets (DNNs) have achieved state-of-the-art performance in 3D detection. The…

Recent advances in 4D imaging radar have enabled robust perception in adverse weather, while camera sensors provide dense semantic information. Fusing the these complementary modalities has great potential for cost-effective 3D perception.…