相关论文: Perceptually Constrained Adversarial Attacks

Recent work has shown that additive threat models, which only permit the addition of bounded noise to the pixels of an image, are insufficient for fully capturing the space of imperceivable adversarial examples. For example, small rotations…

Neural networks are now actively being used for computer vision tasks in security critical areas such as robotics, face recognition, autonomous vehicles yet their safety is under question after the discovery of adversarial attacks. In this…

Adversarial attacks aim to confound machine learning systems, while remaining virtually imperceptible to humans. Attacks on image classification systems are typically gauged in terms of $p$-norm distortions in the pixel feature space. We…

Much research effort has been devoted to better understanding adversarial examples, which are specially crafted inputs to machine-learning models that are perceptually similar to benign inputs, but are classified differently (i.e.,…

Assessing the similarity of two images is a complex task that attracts significant efforts in the image processing community. The widely used Structural Similarity Index Measure (SSIM) addresses this problem by quantifying a perceptual…

Recently, there has been much interest in deep learning techniques to do image compression and there have been claims that several of these produce better results than engineered compression schemes (such as JPEG, JPEG2000 or BPG). A…

Recently, there has been a large amount of work towards fooling deep-learning-based classifiers, particularly for images, via adversarial inputs that are visually similar to the benign examples. However, researchers usually use Lp-norm…

Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion can still compromise these metrics. In our…

The use of the structural similarity index (SSIM) is widespread. For almost two decades, it has played a major role in image quality assessment in many different research disciplines. Clearly, its merits are indisputable in the research…

Traditional image similarity metrics are ineffective at evaluating the similarity between a real image of a scene and an artificially generated version of that viewpoint [6, 9, 13, 14]. Our research evaluates the effectiveness of a new,…

When generating adversarial examples to attack deep neural networks (DNNs), Lp norm of the added perturbation is usually used to measure the similarity between original image and adversarial example. However, such adversarial attacks…

Tractable models of human perception have proved to be challenging to build. Hand-designed models such as MS-SSIM remain popular predictors of human image quality judgements due to their simplicity and speed. Recent modern deep learning…

Pixel-wise losses, e.g., cross-entropy or L2, have been widely used in structured prediction tasks as a spatial extension of generic image classification or regression. However, its i.i.d. assumption neglects the structural regularity…

The Structural Similarity (SSIM) Index is a very widely used image/video quality model that continues to play an important role in the perceptual evaluation of compression algorithms, encoding recipes and numerous other image/video…

Deep neural networks (DNNs) have recently achieved state-of-the-art performance and provide significant progress in many machine learning tasks, such as image classification, speech processing, natural language processing, etc. However,…

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the…

The Structural Similarity Index (SSIM) is generally considered to be a milestone in the recent history of Image Quality Assessment (IQA). Alas, SSIM's accepted development from the product of three heuristic factors continues to obscure…

Deep networks are increasingly being applied to problems involving image synthesis, e.g., generating images from textual descriptions and reconstructing an input image from a compact representation. Supervised training of image-synthesis…

It is now generally accepted that Euclidean-based metrics may not always adequately represent the subjective judgement of a human observer. As a result, many image processing methodologies have been recently extended to take advantage of…

Adversarial defenses are naturally evaluated on their ability to tolerate adversarial attacks. To test defenses, diverse adversarial attacks are crafted, that are usually described in terms of their evading capability and the L0, L1, L2,…