Related papers: Detecting Adversarial Data using Perturbation Forg…
Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…
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…
In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds,more and more DeepFake detection techniques have been proposed. These methods typically rely on detecting statistical differences…
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show…
Various facial manipulation techniques have drawn serious public concerns in morality, security, and privacy. Although existing face forgery classifiers achieve promising performance on detecting fake images, these methods are vulnerable to…
Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models…
Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…
Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced…
An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an…
We present a novel method and analysis to train generative adversarial networks (GAN) in a stable manner. As shown in recent analysis, training is often undermined by the probability distribution of the data being zero on neighborhoods of…
Universal Adversarial Perturbations are image-agnostic and model-independent noise that when added with any image can mislead the trained Deep Convolutional Neural Networks into the wrong prediction. Since these Universal Adversarial…
The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…
Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…
Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…
Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even…
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…
Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical…
Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving…
Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. Unfortunately, estimating or comparing two data distributions is extremely…
In this paper, we propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors and make it easier to simulate the output distribution of a deep neural…