相关论文: Normal vs. Adversarial: Salience-based Analysis of…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Adversarial examples, generated by adding small but intentionally imperceptible perturbations to normal examples, can mislead deep neural networks (DNNs) to make incorrect predictions. Although much work has been done on both adversarial…

Transferability of adversarial samples became a serious concern due to their impact on the reliability of machine learning system deployments, as they find their way into many critical applications. Knowing factors that influence…

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…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Deep neural networks have been shown to be vulnerable to adversarial examples---maliciously crafted examples that can trigger the target model to misbehave by adding imperceptible perturbations. Existing attack methods for k-nearest…

Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains.…

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we investigate an attack-agnostic defense against adversarial attacks on…

We study cross-lingual sequence tagging with little or no labeled data in the target language. Adversarial training has previously been shown to be effective for training cross-lingual sentence classifiers. However, it is not clear if…

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this…

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Recent years have witnessed the deployment of adversarial attacks to evaluate the robustness of Neural Networks. Past work in this field has relied on traditional optimization algorithms that ignore the inherent structure of the problem and…

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness of neural networks…

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…

Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…