mlsanityData to 7 Oct 2026

Certified Robustness to Programmable Transformations in LSTMs

arXiv 2102.07818 ↗First posted 15 Feb 2021cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an approach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 26 of its 40 references that are in the map. First posted on arXiv 15 Feb 2021.

Builds on

26 of 40 references.

References · 26

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  4. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  5. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  6. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  7. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  8. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  9. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  10. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  11. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  12. 2017Deep Text Classification Can be Fooledcited by 105
14 more
  1. 2016Crafting Adversarial Input Sequences for Recurrent Neural Networkscited by 102
  2. 2020SoK: Certified Robustness for Deep Neural Networkscited by 100
  3. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  4. 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
  5. 2020Robustness Verification for Transformerscited by 76
  6. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  7. 2019On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Modelscited by 56
  8. 2020Generating Fluent Adversarial Examples for Natural Languagescited by 49
  9. 2018Robust Machine Comprehension Models via Adversarial Trainingcited by 44
  10. 2019POPQORN: Quantifying Robustness of Recurrent Neural Networkscited by 36
  11. 2020Verifying Recurrent Neural Networks using Invariant Inferencecited by 25
  12. 2018Comparing Attention-based Convolutional and Recurrent Neural Networks: Success and Limitations in Machine Reading Comprehensioncited by 19
  13. 2020Adversarial Attacks and Defense on Texts: A Surveycited by 12
  14. 2020Robustness to Programmable String Transformations via Augmented Abstract Trainingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 5; 2024: 4; 2025: 1; 2026: 2.

18 papers.

Sort:

  1. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  2. 2022Interactive Model Cards: A Human-Centered Approach to Model Documentationcited by 61
  3. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  4. 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletioncited by 17
  5. 2024NLP Verification: Towards a General Methodology for Certifying Robustnesscited by 14
  6. 2024Spiking Convolutional Neural Networks for Text Classificationcited by 10
  7. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  8. 2023ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verificationcited by 6
  9. 2023PECAN: A Deterministic Certified Defense Against Backdoor Attackscited by 5
  10. 2021The Fundamental Limits of Interval Arithmetic for Neural Networkscited by 4
  11. 2023Reliability Assurance for Deep Neural Network Architectures Against Numerical Defectscited by 3
  12. 2024Verified Training for Counterfactual Explanation Robustness under Data Shiftcited by 2
6 more
  1. 2022Natural Language Specifications in Proof Assistantscited by 1
  2. 2025Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approachcited by 1
  3. 2022Why Robust Natural Language Understanding is a Challengecited by 0
  4. 2024A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustnesscited by 0
  5. 2026Robustness Verification of Recurrent Neural Networks with Abstraction Refinementcited by 0
  6. 2026S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLPcited by 0