Related papers: A Versatile Framework for Designing Group-Sparse A…

This study investigates the vulnerability of semantic segmentation models to adversarial input perturbations, in the domain of off-road autonomous driving. Despite good performance in generic conditions, the state-of-the-art classifiers are…

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating…

Semantic layouts based Image synthesizing, which has benefited from the success of Generative Adversarial Network (GAN), has drawn much attention in these days. How to enhance the synthesis image equality while keeping the stochasticity of…

Deep neural networks (DNNs) have achieved great success in image classification, but can be very vulnerable to adversarial attacks with small perturbations to images. To improve adversarial image generation for DNNs, we develop a novel…

Although deep learning has made remarkable progress in processing various types of data such as images, text and speech, they are known to be susceptible to adversarial perturbations: perturbations specifically designed and added to the…

A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which lead to incorrect predictions. Unfortunately, most literature…

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…

The rapid adoption of machine learning (ML) technologies has driven organizations across diverse sectors to seek efficient and reliable methods to accelerate model development-to-deployment. Machine Learning Operations (MLOps) has emerged…

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs). In this paper, we make the case that sparse representations of the input data are a crucial tool for combating…

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…

We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted…

In this paper, we propose a novel image denoising algorithm exploiting features from both spatial as well as transformed domain. We implement intensity-invariance based improved grouping for collaborative support-agnostic sparse…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately…

Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g.,…

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

The offensive security landscape is highly fragmented: enterprise platforms avoid memory-corruption vulnerabilities due to Denial of Service (DoS) risks, Automatic Exploit Generation (AEG) systems suffer from semantic blindness, and Large…

Graph neural networks have been widely utilized to solve graph-related tasks because of their strong learning power in utilizing the local information of neighbors. However, recent studies on graph adversarial attacks have proven that…

Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting.…