mlsanityData to 7 Oct 2026

Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples

arXiv 1803.01128 ↗First posted 3 Mar 2018cs.LGcited by 93

Not on the map. Why?

Abstract (arXiv)

Crafting adversarial examples has become an important technique to evaluate the robustness of deep neural networks (DNNs). However, most existing works focus on attacking the image classification problem since its input space is continuous and output space is finite. In this paper, we study the much more challenging problem of crafting adversarial examples for sequence-to-sequence (seq2seq) models, whose inputs are discrete text strings and outputs have an almost infinite number of possibilities. To address the challenges caused by the discrete input space, we propose a projected gradient method combined with group lasso and gradient regularization. To handle the almost infinite output space, we design some novel loss functions to conduct non-overlapping attack and targeted keyword attack. We apply our algorithm to machine translation and text summarization tasks, and verify the effectiveness of the proposed algorithm: by changing less than 3 words, we can make seq2seq model to produce desired outputs with high success rates. On the other hand, we recognize that, compared with the well-evaluated CNN-based classifiers, seq2seq models are intrinsically more robust to adversarial attacks.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 15; 2023: 20; 2024: 16; 2025: 8; 2026: 2.

93 papers.

Sort:

By area:

  1. 2022Red Teaming Language Models with Language Modelscited by 983
  2. 2023RADAR: Robust AI-Text Detection via Adversarial Learningcited by 187
  3. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  4. 2021Trustworthy AI: A Computational Perspectivecited by 93
  5. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  6. 2021Towards Improving Adversarial Training of NLP Modelscited by 79
  7. 2021Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasurescited by 69
  8. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  9. 2021Adversarial Attacks On Multi-Agent Communicationcited by 48
  10. 2022On the Blind Spots of Model-Based Evaluation Metrics for Text Generationcited by 48
  11. 2021Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Datacited by 45
  12. 2021Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustnesscited by 43
38 more
  1. 2022SemAttack: Natural Textual Attacks via Different Semantic Spacescited by 42
  2. 2022Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overviewcited by 37
  3. 2024Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluationcited by 37
  4. 2021Dual-Key Multimodal Backdoors for Visual Question Answeringcited by 35
  5. 2021Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Modelscited by 29
  6. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  7. 2022Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitutioncited by 28
  8. 2023A Survey on Out-of-Distribution Evaluation of Neural NLP Modelscited by 20
  9. 2021Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Modelscited by 17
  10. 2021Efficient Combinatorial Optimization for Word-level Adversarial Textual Attackcited by 17
  11. 2022Reverse Engineering of Imperceptible Adversarial Image Perturbationscited by 17
  12. 2021The King is Naked: on the Notion of Robustness for Natural Language Processingcited by 16
  13. 2022LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Modelscited by 16
  14. 2024HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Textcited by 16
  15. 2021On Robustness of Neural Semantic Parserscited by 14
  16. 2024Towards Building a Robust Toxicity Predictorcited by 14
  17. 2021Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profilingcited by 12
  18. 2021Token-Modification Adversarial Attacks for Natural Language Processing: A Surveycited by 12
  19. 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attackcited by 12
  20. 2023TransFool: An Adversarial Attack against Neural Machine Translation Modelscited by 12
  21. 2023White-Box Multi-Objective Adversarial Attack on Dialogue Generationcited by 12
  22. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  23. 2023Dynamic Transformers Provide a False Sense of Efficiencycited by 11
  24. 2024Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Stepcited by 11
  25. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  26. 2023Targeted Adversarial Attacks against Neural Machine Translationcited by 10
  27. 2021Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluationcited by 9
  28. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  29. 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 9
  30. 2024An Empirical Study of In-context Learning in LLMs for Machine Translationcited by 9
  31. 2021Evaluating Document Coherence Modellingcited by 8
  32. 2022Residue-Based Natural Language Adversarial Attack Detectioncited by 8
  33. 2023Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equationscited by 8
  34. 2023Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Textcited by 8
  35. 2021Improving the robustness and accuracy of biomedical language models through adversarial trainingcited by 7
  36. 2021Spinning Sequence-to-Sequence Models with Meta-Backdoorscited by 5
  37. 2023BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spacescited by 5
  38. 2022FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustnesscited by 4

50 most cited of 93 All 93 (JSON)