相关论文: Utilizing Adversarial Examples for Bias Mitigation…

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that…

This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. Deep learning classification models are often trained using datasets that mirror real-world scenarios. In this…

Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce…

Compared with traditional machine learning models, deep neural networks perform better, especially in image classification tasks. However, they are vulnerable to adversarial examples. Adding small perturbations on examples causes a…

Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data…

Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…

Adversarial examples are inputs for machine learning models that have been designed by attackers to cause the model to make mistakes. In this paper, we demonstrate that adversarial examples can also be utilized for good to improve the…

Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes…

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs. Currently, a large number of researches on defending adversarial…

While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…

In recent years, fairness has become an important topic in the machine learning research community. In particular, counterfactual fairness aims at building prediction models which ensure fairness at the most individual level. Rather than…

We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an…

Due to the limited availability of medical data, deep learning approaches for medical image analysis tend to generalise poorly to unseen data. Augmenting data during training with random transformations has been shown to help and became a…

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object…