Related papers: Interpreting Structured Perturbations in Image Pro…

Image generation models trained on large datasets can synthesize high-quality images but often produce spatially inconsistent and distorted images due to limited information about the underlying structures and spatial layouts. In this work,…

3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time and high-fidelity 3D reconstruction from posed images. However, recent studies reveal its vulnerability to adversarial corruptions in input views, where…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Deep learning offers state of the art solutions for image recognition. However, deep models are vulnerable to adversarial perturbations in images that are subtle but significantly change the model's prediction. In a white-box attack, these…

This study explores the impact of adversarial perturbations on Convolutional Neural Networks (CNNs) with the aim of enhancing the understanding of their underlying mechanisms. Despite numerous defense methods proposed in the literature,…

Deep convolutional neural networks accurately classify a diverse range of natural images, but may be easily deceived when designed, imperceptible perturbations are embedded in the images. In this paper, we design a multi-pronged training,…

Generative modeling frameworks have emerged as an effective approach to capture high-dimensional image distributions from large datasets without requiring domain-specific knowledge, a capability essential for longitudinal disease…

Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing…

Input transformation based defense strategies fall short in defending against strong adversarial attacks. Some successful defenses adopt approaches that either increase the randomness within the applied transformations, or make the defense…

Input space reconstruction is an attractive representation learning paradigm. Despite interpretability of the reconstruction and generation, we identify a misalignment between learning by reconstruction, and learning for perception. We show…

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Deep learning-based face recognition models are vulnerable to adversarial attacks. To curb these attacks, most defense methods aim to improve the robustness of recognition models against adversarial perturbations. However, the…

As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and label their AI-generated content, which can mitigate the…

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Adversarial examples are malicious images with visually imperceptible perturbations. While these carefully crafted perturbations restricted with tight…

Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force…

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…

Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society. Many methods have been proposed to detect fake images, but they are vulnerable to adversarial perturbations…

The proliferation of generative video models has made detecting AI-generated and manipulated videos an urgent challenge. Existing detection approaches often fail to generalize across diverse manipulation types due to their reliance on…

As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously…

Image downscaling is one of the key operations in recent display technology and visualization tools. By this process, the dimension of an image is reduced, aiming to preserve structural integrity and visual fidelity. In this paper, we…