Deep Neural Networks (DNNs) are widely used in Natural Language Processing (NLP). However, adversarial samples attack benign inputs to readily fool the DNN models. The detection of these samples is a significant challenge that has received little attention in textual domains. Existing defense strategies either assume prior knowledge of specific threats or do not perform well on complex models. In this article, we provide a new framework, namely TADD for detecting textual adversarial samples by leveraging the interpretability of DNNs. In particular, we distinguish between the adversarial distribution and the benign distribution for the decision boundary of the victim models. Our method applies to NLP tasks and does not require re-training victim models and prior knowledge of adversarial attack methods. We evaluate our detector against the state-of-the-art attack methods on various real-world datasets. As demonstrated in the extensive experiments, our approach effectively discriminates between adversarial and benign samples. Additionally, our method is competitive against unseen attacks, reflecting its ability to discover new adversarial samples generated by future attack methods.

The distractor generation task focuses on generating incorrect but plausible options for objective questions such as fill-in-the-blank and multiple-choice questions.This task is widely utilized in educational settings across various domains and subjects.The effectiveness of these questions in assessments relies on the quality of the distractors, as they challenge examinees to select the correct answer from a set of misleading options.The evolution of artificial intelligence (AI) has transitioned the task from traditional methods to the use of neural networks and pre-trained language models.This shift has established new benchmarks and expanded the use of advanced deep learning methods in generating distractors.This survey explores distractor generation tasks, datasets, methods, and current evaluation metrics for English objective questions, covering both textbased and multi-modal domains.It also evaluates existing AI models and benchmarks and discusses potential future research directions 1 .Distractor Generation Survey Evaluation (4) Automatic (4.1) Manual (4.2) Auto Metrics N-gram based (4.1.2)E.g.BLEU (Papineni et al., 2002) Ranking-based (4.1.1)E.g.NDCG (Järvelin and Kekäläinen, 2002) Methods (3) AI Models Other Models (3.4)

Deep Neural Networks (DNNs) have achieved high accuracy in multiple Natural Language Processing (NLP) applications. The great success lies in the test data is drawn from the same distribution of the training samples. However, researches have found that the current models classify out-of-distribution, adversarial, and erroneous samples incorrectly with high confidence. Researchers also find the problem comes from the softmax layer of DNN. In this paper, we address this issue and propose a method that ignores the softmax layer in the DNN architecture. Specifically, we estimate the training samples' parameters of the output of the pre-softmax layer of DNN using the Dirichlet Process Gaussian Mixture Model (DPGMM). Then, we compute the distance between a test sample and the distribution of the training samples using Mahalanobis distance to get the classification results. We evaluate our method on a classic NLP task, sentiment analysis, by conducting extensive experiments on different models across several real-world datasets. The results demonstrate that our method assigns correct labels to the samples that are misclassified by current DNNs with softmax layer. Our method can be generalized to any pre-trained DNN without the need to re-train the models and it also does not need supervision learning.

Deep Neural Networks (DNNs) have gained significant popularity in various Natural Language Processing tasks. However, the lack of interpretability of DNNs induces challenges to evaluate the robustness of DNNs. In this paper, we particularly focus on DNNs on sentiment analysis and conduct an empirical investigation on the sensitivity of DNNs. Specifically, we apply a scoring function to rank words importance without depending on the parameters or structure of the deep neural model. Then, we scan characteristics of these words to identify the model's weakness and perturb words to craft targeted attacks that exploit this weakness. We conduct extensive experiments on different neural network models across several real-world datasets. We report four intriguing findings: i) modern deep learning models for sentiment analysis ignore important sentiment terms such as opinion adjectives (i.e., amazing or terrible), ii) adjective words contribute to fooling sentiment analysis models more than other Parts-of-Speech (POS) categories, iii) changing or removing up to 10 adjectives words in a review text only decreases the accuracy up to 2%, and iv) modern models are unable to recognize the difference between an objective and a subjective review text1.

Deep Neural Networks (DNNs) have achieved remarkable results in multiple Natural Language Processing (NLP) applications. However, current studies have found that DNNs can be fooled when using modified samples, namely adversarial examples. This work, specifically, examines DNNs for sentiment analysis using adversarial examples. We particularly aim to examine the impact of modifying the Part-Of-Speech (POS) of words on the input sentences. We conduct extensive experiments on different neural network models across several real-world datasets. The results demonstrate that current DNN models for sentiment analysis are brittle with perturbed noisy words that humans do not have trouble understanding. An interesting finding is that adjective words (Adj) and the combination of adjective and adverb words (Adj-Adv) provide obvious contribution to fooling sentiment analysis DNN models1.

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 are vulnerable to strategically modified samples, named adversarial examples . These samples are generated with some imperceptible perturbations, but can fool the DNNs to give false predictions. Inspired by the popularity of generating adversarial examples against DNNs in Computer Vision (CV), research efforts on attacking DNNs for Natural Language Processing (NLP) applications have emerged in recent years. However, the intrinsic difference between image (CV) and text (NLP) renders challenges to directly apply attacking methods in CV to NLP. Various methods are proposed addressing this difference and attack a wide range of NLP applications. In this article, we present a systematic survey on these works. We collect all related academic works since the first appearance in 2017. We then select, summarize, discuss, and analyze 40 representative works in a comprehensive way. To make the article self-contained, we cover preliminary knowledge of NLP and discuss related seminal works in computer vision. We conclude our survey with a discussion on open issues to bridge the gap between the existing progress and more robust adversarial attacks on NLP DNNs.