mlsanityData to 7 Oct 2026

Certified Robustness Against Natural Language Attacks by Causal Intervention

arXiv 2205.12331 ↗First posted 24 May 2022cs.LG cs.CL cs.CRcited by 23

Not on the map. Why?

Abstract (arXiv)

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Intervention by Semantic Smoothing (CISS), a novel framework towards robustness against natural language attacks. Instead of merely fitting observational data, CISS learns causal effects p(y|do(x)) by smoothing in the latent semantic space to make robust predictions, which scales to deep architectures and avoids tedious construction of noise customized for specific attacks. CISS is provably robust against word substitution attacks, as well as empirically robust even when perturbations are strengthened by unknown attack algorithms. For example, on YELP, CISS surpasses the runner-up by 6.7% in terms of certified robustness against word substitutions, and achieves 79.4% empirical robustness when syntactic attacks are integrated.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 50 of its 73 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

50 of 73 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  9. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
38 more
  1. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  2. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  3. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  4. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  5. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  6. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  7. 2018Generating Natural Language Adversarial Examplescited by 422
  8. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  9. 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
  10. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  11. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  12. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  13. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  14. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  15. 2019Causality for Machine Learningcited by 242
  16. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  17. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 203
  18. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  19. 2017Generating Natural Adversarial Examplescited by 182
  20. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  21. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
  22. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  23. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  24. 2020Interventional Few-Shot Learningcited by 112
  25. 2021Counterfactual Generative Networkscited by 111
  26. 2017Deep Text Classification Can be Fooledcited by 105
  27. 2017Deceiving Google's Perspective API Built for Detecting Toxic Commentscited by 99
  28. 2019Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systemscited by 99
  29. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  30. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  31. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  32. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  33. 2020A Causal View on Robustness of Neural Networkscited by 53
  34. 2018Training verified learners with learned verifierscited by 50
  35. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  36. 2020Few-shot Domain Adaptation by Causal Mechanism Transfercited by 47
  37. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  38. 2019When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 12; 2025: 0; 2026: 1.

23 papers.

Sort:

By area:

  1. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  2. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 87
  3. 2024Building Guardrails for Large Language Modelscited by 61
  4. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learningcited by 47
  5. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 44
  6. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 32
  7. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  8. 2024Large Language Models and Causal Inference in Collaboration: A Surveycited by 26
  9. 2023Certified Robustness for Large Language Models with Self-Denoisingcited by 23
  10. 2022Textual Manifold-based Defense Against Natural Language Adversarial Examplescited by 19
  11. 2024Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuningcited by 16
  12. 2024Advancing the Robustness of Large Language Models through Self-Denoised Smoothingcited by 15
11 more
  1. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  2. 2024Fast Adversarial Training against Textual Adversarial Attackscited by 7
  3. 2023Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attackscited by 5
  4. 2024A survey of recent methods for addressing AI fairness and bias in biomedicinecited by 5
  5. 2024Evaluating and Safeguarding the Adversarial Robustness of Retrieval-Based In-Context Learningcited by 4
  6. 2024KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Modelscited by 3
  7. 2024SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attackscited by 3
  8. 2024Topic-aware Causal Intervention for Counterfactual Detectioncited by 1
  9. 2023Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Modelscited by 0
  10. 2023Machine Learning and Knowledge: Why Robustness Matterscited by 0
  11. 2026The Power of Order: Fooling LLMs with Adversarial Table Permutationscited by 0