相关论文: CNCA: Toward Customizable and Natural Generation o…

Camera-based object detection systems play a vital role in autonomous driving, yet they remain vulnerable to adversarial threats in real-world environments. Existing 2D and 3D physical attacks, due to their focus on texture optimization,…

Node injection attacks on Graph Neural Networks (GNNs) have received increasing attention recently, due to their ability to degrade GNN performance with high attack success rates. However, our study indicates that these attacks often fail…

Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely…

In this paper, we propose a natural and robust physical adversarial example attack method targeting object detectors under real-world conditions. The generated adversarial examples are robust to various physical constraints and visually…

There is considerable evidence that deep neural networks are vulnerable to adversarial perturbations applied directly to their digital inputs. However, it remains an open question whether this translates to vulnerabilities in real systems.…

Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically meaningful perturbations. Current unrestricted adversarial…

As face recognition becomes more widespread in government and commercial services, its potential misuse raises serious concerns about privacy and civil rights. To counteract this threat, various anti-facial recognition techniques have been…

The existence of adversarial attacks on convolutional neural networks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking…

Nowadays, cameras equipped with AI systems can capture and analyze images to detect people automatically. However, the AI system can make mistakes when receiving deliberately designed patterns in the real world, i.e., physical adversarial…

Recent Customized Portrait Generation (CPG) methods, taking a facial image and a textual prompt as inputs, have attracted substantial attention. Although these methods generate high-fidelity portraits, they fail to prevent the generated…

Adversarial patches, often used to provide physical stealth protection for critical assets and assess perception algorithm robustness, usually neglect the need for visual harmony with the background environment, making them easily…

With the great development of generative model techniques, face forgery detection draws more and more attention in the related field. Researchers find that existing face forgery models are still vulnerable to adversarial examples with…

The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing methods of…

While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy.…

Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions.…

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…

Generating photorealistic driving videos has seen significant progress recently, but current methods largely focus on ordinary, non-adversarial scenarios. Meanwhile, efforts to generate adversarial driving scenarios often operate on…

Robust environment perception is critical for autonomous cars, and adversarial defenses are the most effective and widely studied ways to improve the robustness of environment perception. However, all of previous defense methods decrease…

Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial…

The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks. However, deep learning models are notoriously sensitive to adversarial examples which are…