Related papers: A Universal Adversarial Policy for Text Classifier…
Despite their advances and success, real-world deep neural networks are known to be vulnerable to adversarial attacks. Universal adversarial perturbation, an input-agnostic attack, poses a serious threat for them to be deployed in…
Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial…
Neural networks have demonstrated state-of-the-art performance in various machine learning fields. However, the introduction of malicious perturbations in input data, known as adversarial examples, has been shown to deceive neural network…
Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an…
Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…
Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…
This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to…
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made…
Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…
Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a…
Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain…
Recently, with the advancement of deep learning, several applications in text classification have advanced significantly. However, this improvement comes with a cost because deep learning is vulnerable to adversarial examples. This weakness…
Modern classification algorithms are susceptible to adversarial examples--perturbations to inputs that cause the algorithm to produce undesirable behavior. In this work, we seek to understand and extend adversarial examples across domains…
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of…
Adversarial attacks can generate adversarial inputs by applying small but intentionally worst-case perturbations to samples from the dataset, which leads to even state-of-the-art deep neural networks outputting incorrect answers with high…
Adversarial examples are carefully crafted attack points that are supposed to fool machine learning classifiers. In the last years, the field of adversarial machine learning, especially the study of perturbation-based adversarial examples,…
We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment tasks. Our proposed…