Related papers: ReinforceBug: A Framework to Generate Adversarial …
Neural machine translation systems tend to fail on less decent inputs despite its significant efficacy, which may significantly harm the credibility of this systems-fathoming how and when neural-based systems fail in such cases is critical…
Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…
Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…
Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive…
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…
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities.…
The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the…
Adversarial attacks against Deep Neural Networks have been widely studied. One significant feature that makes such attacks particularly powerful is transferability, where the adversarial examples generated from one model can be effective…
Various techniques are used in the generation of adversarial examples, including methods such as TextBugger which introduce minor, hardly visible perturbations to words leading to changes in model behaviour. Another class of techniques…
While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…
Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness…
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can…
Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model's predictions. However, the transferability has not been…
Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted…
Adversarial examples are small and often imperceptible perturbations crafted to fool machine learning models. These attacks seriously threaten the reliability of deep neural networks, especially in security-sensitive domains. Evasion…
Deep learning (DL) has significantly transformed cybersecurity, enabling advancements in malware detection, botnet identification, intrusion detection, user authentication, and encrypted traffic analysis. However, the rise of adversarial…
Research shows that natural language processing models are generally considered to be vulnerable to adversarial attacks; but recent work has drawn attention to the issue of validating these adversarial inputs against certain criteria (e.g.,…
Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…
Adversarial training, which minimizes the maximal risk for label-preserving input perturbations, has proved to be effective for improving the generalization of language models. In this work, we propose a novel adversarial training…