Word-level Textual Adversarial Attacking as Combinatorial Optimization

By Saied Alshahrani

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Han
2. Xipeng Qiu
3. Zhe Gan
4. Zhiyuan Liu
5. Jianfeng Gao
6. Xiao Liu
7. Minlie Huang
8. Maosong Sun

Citations in the corpus

• Pre-Trained Models: Past, Present and Future (2021, background): “For example, PTMs can be easily fooled by synonym replacement (Jin et al., 2020; Zang et al., 2020; Wang et al., 2021a).”
• ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (2020, methodology): “Here we refer to previous work on generating textual adversarial samples using PSO in the discrete search space and adapt their method to our specific problem setting (Zang et al., 2020).”
• A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement (2022, background): “In recent years, a series of adversarial attack methods have been proposed, ranging from character-level word misspelling [ Ebrahimi et al. , 2018 ] , word-level substitution [ Zang et al. , 2020 ] to sentence-level paraphrasing [ Pei et al. , 2020 ] .”
• Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces (2020, methodology): “Jin et al. (2019) uses word embeddings to craft candidate list S to find substitutions while Zang et al. (2020) uses knowledge extracted from Word-Net (Fellbaum, 1998).”
• Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks (2021, background): “…works have demonstrated that PTMs suffer from various kinds of attacks including adversarial attacks (Goodfellow et al., 2015; Jin et al., 2020; Zang et al., 2020), back-door attacks (Gu et al., 2017; Kurita et al., 2020; Ji et al., 2018, 2019; Schuster et al., 2020), and privacy attacks…”
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models (2021, methodology): “However, recent studies [24, 57, 50, 29, 13] reveal that even these large-scale language models are vulnerable to carefully crafted adversarial examples, which can fool the models to output arbitrarily wrong answers by perturbing input sentences in a human-imperceptible way.”
• TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP (2020, methodology): “…new methods for generating adversarial examples and better approaches to defending against these adversaries (Alzantot et al., 2018; Jin et al., 2019; Kuleshov et al., 2018; Li et al., 2019; Gao et al., 2018; Wang et al., 2019; Ebrahimi et al., 2017; Zang et al., 2020; Pruthi et al., 2019).”
• CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding (2021, unknown): “However, recent works show that PLMs suffer from poor robustness when encountering adversarial examples (Jin et al., 2020; Li et al., 2020; Garg and Ramakrishnan, 2020; Zang et al., 2020; Lin et al., 2020a).”
• Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021, background): “Adversarial attacks (Szegedy et al., 2014; Good-fellow et al., 2015; Xu et al., 2020; Zang et al., 2020) are a kind of widely studied security threat to DNNs.”