相关论文: Revisiting Image Classifier Training for Improved …

Adversarial patch-based attacks have shown to be a major deterrent towards the reliable use of machine learning models. These attacks involve the strategic modification of localized patches or specific image areas to deceive trained machine…

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…

Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manually collecting a new training dataset that contains adequate…

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on…

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked…

Protecting image manipulation detectors against perfect knowledge attacks requires the adoption of detector architectures which are intrinsically difficult to attack. In this paper, we do so, by exploiting a recently proposed…

Vertex classification -- the problem of identifying the class labels of nodes in a graph -- has applicability in a wide variety of domains. Examples include classifying subject areas of papers in citation networks or roles of machines in a…

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Deep neural networks are proven to be vulnerable to fine-designed adversarial examples, and adversarial defense algorithms draw more and more attention nowadays. Pre-processing based defense is a major strategy, as well as learning robust…

In this paper, we develop improved techniques for defending against adversarial examples at scale. First, we implement the state of the art version of adversarial training at unprecedented scale on ImageNet and investigate whether it…

Recent learning-based multi-view stereo (MVS) methods show excellent performance with dense cameras and small depth ranges. However, non-learning based approaches still outperform for scenes with large depth ranges and sparser wide-baseline…

Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on…

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Adversarial patch attacks pose a practical threat to deep learning models by forcing targeted misclassifications through localized perturbations, often realized in the physical world. Existing defenses typically assume prior knowledge of…