Related papers: Model Agnostic Answer Reranking System for Adversa…
Popular QA benchmarks like SQuAD have driven progress on the task of identifying answer spans within a specific passage, with models now surpassing human performance. However, retrieving relevant answers from a huge corpus of documents is…
Automatic scoring engines have been used for scoring approximately fifteen million test-takers in just the last three years. This number is increasing further due to COVID-19 and the associated automation of education and testing. Despite…
Unsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to construct data and train QA models. However, most of these…
Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…
The vulnerability of machine learning models to adversarial attacks remains a critical security challenge. Traditional defenses, such as adversarial training, typically robustify models by minimizing a worst-case loss. However, these…
Recently, the area of adversarial attacks on image quality metrics has begun to be explored, whereas the area of defences remains under-researched. In this study, we aim to cover that case and check the transferability of adversarial…
Current textual question answering models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns in the data, so they fail to generalize to out-of-distribution settings. To make a more robust…
Software with natural-language user interfaces has an ever-increasing importance. However, the quality of the included Question Answering (QA) functionality is still not sufficient regarding the number of questions that are answered…
Question Answering (QA) tasks requiring information from multiple documents often rely on a retrieval model to identify relevant information for reasoning. The retrieval model is typically trained to maximize the likelihood of the labeled…
Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents.Though many models for single-document machine comprehension have achieved strong performance, there is still much room for…
Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been…
Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract…
Promptly and accurately answering questions on products is important for e-commerce applications. Manually answering product questions (e.g. on community question answering platforms) results in slow response and does not scale. Recent…
This paper studies joint models for selecting correct answer sentences among the top $k$ provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) systems. Our work shows that…
Adversarial examples are one of the most severe threats to deep learning models. Numerous works have been proposed to study and defend adversarial examples. However, these works lack analysis of adversarial information or perturbation,…
Most adversarial attack defense methods rely on obfuscating gradients. These methods are successful in defending against gradient-based attacks; however, they are easily circumvented by attacks which either do not use the gradient or by…
Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans. To address this problem, we propose a novel network called…
This paper proposes a new defense approach for counteracting state-of-the-art white and black-box adversarial attack algorithms. Our approach fits into the implicit reactive defense algorithm category since it does not directly manipulate…
Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless…
With the wide adoption of machine learning techniques, requirements have evolved beyond sheer high performance, often requiring models to be trustworthy. A common approach to increase the trustworthiness of such systems is to allow them to…