SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator
Not on the map. Why?
Abstract (arXiv)
Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that produce high-quality AEs. Developing such models has been much slower in natural language processing (NLP) than in areas such as computer vision. This paper introduces a practical and efficient adversarial attack model called SSCAE for Semantic, Syntactic, and Context-aware natural language AEs generator. SSCAE identifies important words and uses a masked language model to generate an early set of substitutions. Next, two well-known language models are employed to evaluate the initial set in terms of semantic and syntactic characteristics. We introduce (1) a dynamic threshold to capture more efficient perturbations and (2) a local greedy search to generate high-quality AEs. As a black-box method, SSCAE generates humanly imperceptible and context-aware AEs that preserve semantic consistency and the source language's syntactical and grammatical requirements. The effectiveness and superiority of the proposed SSCAE model are illustrated with fifteen comparative experiments and extensive sensitivity analysis for parameter optimization. SSCAE outperforms the existing models in all experiments while maintaining a higher semantic consistency with a lower query number and a comparable perturbation rate.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 18 Mar 2024.
Builds on
33 of 63 references.
References · 33
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
21 more
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2016Adversarial examples in the physical worldcited by 1,762
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
- 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
- 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
- 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
- 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
- 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
- 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
- 2016Enhanced LSTM for Natural Language Inferencecited by 199
- 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
- 2018Universal Adversarial Trainingcited by 85
- 2020Universal Adversarial Attacks with Natural Triggers for Text Classificationcited by 50
- 2020Generating Natural Language Attacks in a Hard Label Black Box Settingcited by 50
- 2022PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Modelscited by 44
- 2022Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Modelscited by 37
- 2022Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimizationcited by 22
- 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
- 2021Unsupervised Editing for Counterfactual Storiescited by 8
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.