Related papers: Generating Textual Adversaries with Minimal Pertur…
We propose a probabilistic perspective on adversarial examples, allowing us to embed subjective understanding of semantics as a distribution into the process of generating adversarial examples, in a principled manner. Despite significant…
Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics,…
In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or…
Warning: this paper contains content that maybe offensive or upsetting. Recent research in Natural Language Processing (NLP) has advanced the development of various toxicity detection models with the intention of identifying and mitigating…
Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even…
Safety classifiers are critical in mitigating toxicity on online forums such as social media and in chatbots. Still, they continue to be vulnerable to emergent, and often innumerable, adversarial attacks. Traditional automated adversarial…
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…
While deep learning is remarkably successful on perceptual tasks, it was also shown to be vulnerable to adversarial perturbations of the input. These perturbations denote noise added to the input that was generated specifically to fool the…
Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…
The landscape of available textual adversarial attacks keeps growing, posing severe threats and raising concerns regarding the deep NLP system's integrity. However, the crucial problem of defending against malicious attacks has only drawn…
This paper addresses the problem of manipulating images using natural language description. Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance. Although…
We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding such perturbations.…
Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness,…
Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constraint), suitable for interpreting the vulnerability of DNNs.…
We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks…
Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…
NLP researchers propose different word-substitute black-box attacks that can fool text classification models. In such attack, an adversary keeps sending crafted adversarial queries to the target model until it can successfully achieve the…
With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous…
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…
Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial…