相关论文: Beyond Explainability: Leveraging Interpretability…

Sometimes it is not enough for a DNN to produce an outcome. For example, in applications such as healthcare, users need to understand the rationale of the decisions. Therefore, it is imperative to develop algorithms to learn models with…

Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible…

The convergence of cross-modal adversarial learning and physics-driven methods represents a cutting-edge direction for tackling challenges in complex multi-modal tasks and scientific computing. This review focuses on systematically…

The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, we have yet to…

Injecting adversarial examples during training, known as adversarial training, can improve robustness against one-step attacks, but not for unknown iterative attacks. To address this challenge, we first show iteratively generated…

We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained CNNs…

Two key challenges within Reinforcement Learning involve improving (a) agent learning within environments with sparse extrinsic rewards and (b) the explainability of agent actions. We describe a curious subgoal focused agent to address both…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

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…

We consider the question of learnability of distribution classes in the presence of adaptive adversaries -- that is, adversaries capable of intercepting the samples requested by a learner and applying manipulations with full knowledge of…

Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use contextual reasoning…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain"…

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such…

Adversarial robustness is essential for security and reliability of machine learning systems. However, adversarial robustness enhanced by defense algorithms is easily erased as the neural network's weights update to learn new tasks. To…