相关论文: On Adversarial Examples for Character-Level Neural…

Deep learning based systems are susceptible to adversarial attacks, where a small, imperceptible change at the input alters the model prediction. However, to date the majority of the approaches to detect these attacks have been designed for…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and…

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…

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose…

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…

Exposing diverse subword segmentations to neural machine translation (NMT) models often improves the robustness of machine translation as NMT models can experience various subword candidates. However, the diversification of subword…

Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs. In this work, we revisit the DNN training process that includes…

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include…

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…

While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions. In this work, we introduce…

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…

As deep learning (DL) models are increasingly being integrated into our everyday lives, ensuring their safety by making them robust against adversarial attacks has become increasingly critical. DL models have been found to be susceptible to…

Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While…

While the literature on security attacks and defense of Machine Learning (ML) systems mostly focuses on unrealistic adversarial examples, recent research has raised concern about the under-explored field of realistic adversarial attacks and…

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting. Black box attacks are particularly…

We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT,…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…