mlsanityData to 14 Oct 2026

Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data

arXiv 1805.12316 ↗First posted 31 May 2018cs.LG cs.AI cs.CLcited by 38

Not on the map. Why?

Abstract (arXiv)

We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of these methods using both quantitative metrics and human evaluation on various state-of-the-art models for text classification, including a word-based CNN, a character-based CNN and an LSTM. As as example of our results, we show that the accuracy of character-based convolutional networks drops to the level of random selection by modifying only five characters through Greedy Attack.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 15; 2022: 11; 2023: 4; 2024: 6; 2025: 2.

38 papers.

Sort:

By area:

  1. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  2. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  3. 2021Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitutioncited by 56
  4. 2022CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Modelscited by 53
  5. 2021Cross-modal Adversarial Reprogrammingcited by 34
  6. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  7. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  8. 2024On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMscited by 25
  9. 2024Data Poisoning for In-context Learningcited by 21
  10. 2022Adversarial Robustness for Tabular Data through Cost and Utility Awarenesscited by 15
  11. 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
  12. 2022Fooling Explanations in Text Classifierscited by 13
26 more
  1. 2023Auditing and Generating Synthetic Data with Controllable Trust Trade-offscited by 13
  2. 2022TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attackcited by 10
  3. 2021Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluationcited by 9
  4. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  5. 2021A Differentiable Language Model Adversarial Attack on Text Classifierscited by 9
  6. 2021Evaluating Document Coherence Modellingcited by 8
  7. 2021Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Modelscited by 5
  8. 2023Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothingcited by 5
  9. 2021Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directionscited by 4
  10. 2024Revisiting Character-level Adversarial Attacks for Language Modelscited by 4
  11. 2021Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Miningcited by 3
  12. 2022Towards Efficient and Domain-Agnostic Evasion Attack with High-dimensional Categorical Inputscited by 3
  13. 2023The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examplescited by 3
  14. 2021Adversarial Machine Learning in Text Analysis and Generationcited by 2
  15. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  16. 2022AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputscited by 2
  17. 2024EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detectioncited by 2
  18. 2025Robustness in Both Domains: CLIP Needs a Robust Text Encodercited by 2
  19. 2022Towards Generating Adversarial Examples on Mixed-type Datacited by 1
  20. 2022Generating Textual Adversaries with Minimal Perturbationcited by 1
  21. 2024Assessing biomedical knowledge robustness in large language models by query-efficient sampling attackscited by 1
  22. 2025A Comprehensive Analysis of Adversarial Attacks against Spam Filterscited by 1
  23. 2021Improved and Efficient Text Adversarial Attacks using Target Informationcited by 0
  24. 2022Probabilistic Categorical Adversarial Attack & Adversarial Trainingcited by 0
  25. 2023Evaluating the Robustness of Conversational Recommender Systems by Adversarial Examplescited by 0
  26. 2024Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methodscited by 0