Related papers: Diffusion-based Adversarial Purification for Intru…
Deep learning has emerged as a powerful approach for malware detection, demonstrating impressive accuracy across various data representations. However, these models face critical limitations in real-world, non-stationary environments where…
Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on…
Machine learning has witnessed tremendous growth in its adoption and advancement in the last decade. The evolution of machine learning from traditional algorithms to modern deep learning architectures has shaped the way today's technology…
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99.9% similar to a benign sample. Given the wide application of DNN-based audio recognition systems,…
Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet…
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method…
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…
Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and…
Diffusion models have demonstrated remarkable performance in image generation tasks, paving the way for powerful AIGC applications. However, these widely-used generative models can also raise security and privacy concerns, such as copyright…
Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain. However, this approach is slow and costly…
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…
Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to…
In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…
Adversarial samples exploit irregularities in the manifold `learned' by deep learning models to cause misclassifications. The study of these adversarial samples provides insight into the features a model uses to classify inputs, which can…
While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a…
We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model…
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…
In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the…
Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…