相关论文: Adversarial Examples for Evaluating Math Word Prob…

Compositional generalization refers to a model's capability to generalize to newly composed input data based on the data components observed during training. It has triggered a series of compositional generalization analysis on different…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Automated math word problem solvers based on neural networks have successfully managed to obtain 70-80\% accuracy in solving arithmetic word problems. However, it has been shown that these solvers may rely on superficial patterns to obtain…

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. Math Word Problems (MWPs) serve as a crucial benchmark for evaluating LLMs' reasoning abilities. While most research primarily focuses on…

Adversarial attacks expose vulnerabilities of deep learning models by introducing minor perturbations to the input, which lead to substantial alterations in the output. Our research focuses on the impact of such adversarial attacks on…

Various techniques are used in the generation of adversarial examples, including methods such as TextBugger which introduce minor, hardly visible perturbations to words leading to changes in model behaviour. Another class of techniques…

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Large language models have many beneficial applications, but can they also be used to attack content-filtering algorithms in social media platforms? We investigate the challenge of generating adversarial examples to test the robustness of…

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…

Recently, deep learning models have made great progress in MWP solving on answer accuracy. However, they are uninterpretable since they mainly rely on shallow heuristics to achieve high performance without understanding and reasoning the…

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage…

Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger…

State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length,…

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing…

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

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…