Related papers: MNIST-C: A Robustness Benchmark for Computer Visio…

Neural networks have demonstrated significant accuracy across various domains, yet their vulnerability to subtle input alterations remains a persistent challenge. Conventional methods like data augmentation, while effective to some extent,…

Recent studies have shown that deep convolutional neural networks (DCNN) are vulnerable to adversarial examples and sensitive to perceptual quality as well as the acquisition condition of images. These findings raise a big concern for the…

Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as…

In our contemporary academic inquiry, we present "Diffusion-C," a foundational methodology to analyze the generative restrictions of Diffusion Models, particularly those akin to GANs, DDPM, and DDIM. By employing input visual data that has…

AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinformation, the detection of AI-generated images is a pressing…

Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have…

Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP,…

We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…

Convolutional neural networks (CNNs) excel in computer vision but are susceptible to adversarial attacks, crafted perturbations designed to mislead predictions. Despite advances in adversarial training, a gap persists between model accuracy…

Despite their excellent performance, state-of-the-art computer vision models often fail when they encounter adversarial examples. Video perception models tend to be more fragile under attacks, because the adversary has more places to…

Vision-based control relies on accurate perception to achieve robustness. However, image distribution changes caused by sensor noise, adverse weather, and dynamic lighting can degrade perception, leading to suboptimal control decisions.…

Convolutional Neural Networks (CNNs) excel at image classification but remain vulnerable to common corruptions that humans handle with ease. A key reason for this fragility is their reliance on local texture cues rather than global object…

The primary tools used to monitor and defend object detectors under adversarial attack assume that when accuracy degrades, detection count drops in tandem. This coupling was assumed, not measured. We report a counterexample observed on a…

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications.…

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

The Virus-MNIST data set is a collection of thumbnail images that is similar in style to the ubiquitous MNIST hand-written digits. These, however, are cast by reshaping possible malware code into an image array. Naturally, it is poised to…

Despite its prevalent use in image-text matching tasks in a zero-shot manner, CLIP has been shown to be highly vulnerable to adversarial perturbations added onto images. Recent studies propose to finetune the vision encoder of CLIP with…

Generalizing visual recognition models trained on a single distribution to unseen input distributions (i.e. domains) requires making them robust to superfluous correlations in the training set. In this work, we achieve this goal by altering…

The recent success of Vision Transformers is shaking the long dominance of Convolutional Neural Networks (CNNs) in image recognition for a decade. Specifically, in terms of robustness on out-of-distribution samples, recent research finds…

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an…