相关论文: Learning Interpretable Features via Adversarially …

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,…

In recent years, there has been significant attention given to the robustness assessment of neural networks. Robustness plays a critical role in ensuring reliable operation of artificial intelligence (AI) systems in complex and uncertain…

In this paper, we present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining high accuracy on clean data. Our method introduces…

Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance…

Interpretability of deep learning is widely used to evaluate the reliability of medical imaging models and reduce the risks of inaccurate patient recommendations. For models exceeding human performance, e.g. predicting RNA structure from…

In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might…

Monumental advances in deep learning have led to unprecedented achievements across various domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial.…

Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard…

Lifted neural networks (i.e. neural architectures explicitly optimizing over respective network potentials to determine the neural activities) can be combined with a type of adversarial training to gain robustness for internal as well as…

To equip Convolutional Neural Networks (CNNs) with explainability, it is essential to interpret how opaque models take specific decisions, understand what causes the errors, improve the architecture design, and identify unethical biases in…

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data, the input training data is disturbed in the description of…

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To…

Deep networks for computer vision are not reliable when they encounter adversarial examples. In this paper, we introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference. By introducing…

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy.…

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…

Deep neural networks (DNNs) are known to have a fundamental sensitivity to adversarial attacks, perturbations of the input that are imperceptible to humans yet powerful enough to change the visual decision of a model. Adversarial attacks…

It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…