Related papers: Using Random Perturbations to Mitigate Adversarial…
It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…
Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…
Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of…
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…
Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…
Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…
The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…
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,…
Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic…
Word sense disambiguation is a well-known source of translation errors in NMT. We posit that some of the incorrect disambiguation choices are due to models' over-reliance on dataset artifacts found in training data, specifically superficial…
Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…
The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…
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…
The surge of state-of-the-art Transformer-based models has undoubtedly pushed the limits of NLP model performance, excelling in a variety of tasks. We cast the spotlight on the underexplored task of Natural Language Inference (NLI), since…
It is known that neural networks are subject to attacks through adversarial perturbations, i.e., inputs which are maliciously crafted through perturbations to induce wrong predictions. Furthermore, such attacks are impossible to eliminate,…
In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning. We create a…
Contrastive learning has proven to be an effective method for pre-training models using weakly labeled data in the vision domain. Sentence transformers are the NLP counterparts to this architecture, and have been growing in popularity due…
Data-driven statistical Natural Language Processing (NLP) techniques leverage large amounts of language data to build models that can understand language. However, most language data reflect the public discourse at the time the data was…
With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…