mlsanityData to 7 Oct 2026

On The Empirical Effectiveness of Unrealistic Adversarial Hardening Against Realistic Adversarial Attacks

arXiv 2202.03277 ↗First posted 7 Feb 2022cs.LG cs.CRcited by 15

Not on the map. Why?

Abstract (arXiv)

While the literature on security attacks and defense of Machine Learning (ML) systems mostly focuses on unrealistic adversarial examples, recent research has raised concern about the under-explored field of realistic adversarial attacks and their implications on the robustness of real-world systems. Our paper paves the way for a better understanding of adversarial robustness against realistic attacks and makes two major contributions. First, we conduct a study on three real-world use cases (text classification, botnet detection, malware detection)) and five datasets in order to evaluate whether unrealistic adversarial examples can be used to protect models against realistic examples. Our results reveal discrepancies across the use cases, where unrealistic examples can either be as effective as the realistic ones or may offer only limited improvement. Second, to explain these results, we analyze the latent representation of the adversarial examples generated with realistic and unrealistic attacks. We shed light on the patterns that discriminate which unrealistic examples can be used for effective hardening. We release our code, datasets and models to support future research in exploring how to reduce the gap between unrealistic and realistic adversarial attacks.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

32 of 46 references.

References · 32

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  10. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  11. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
  12. 2018Generating Natural Language Adversarial Examplescited by 422
20 more
  1. 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 414
  2. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  3. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  4. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  5. 2018Adversarial Robustness Toolbox v1.0.0cited by 214
  6. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
  7. 2020Reevaluating Adversarial Examples in Natural Languagecited by 83
  8. 2018Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learningcited by 60
  9. 2021Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Datacited by 45
  10. 2017Survey of Machine Learning Techniques for Malware Analysiscited by 31
  11. 2020A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuningcited by 30
  12. 2019FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environmentscited by 23
  13. 2021A Unified Framework for Adversarial Attack and Defense in Constrained Feature Spacecited by 22
  14. 2019Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systemscited by 16
  15. 2020ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systemscited by 13
  16. 2020Adversarial Examples in Constrained Domainscited by 11
  17. 2021On the Robustness of Domain Constraintscited by 11
  18. 2020Not All Datasets Are Born Equal: On Heterogeneous Data and Adversarial Examplescited by 9
  19. 2018Evading classifiers in discrete domains with provable optimality guaranteescited by 7
  20. 2019On Designing Machine Learning Models for Malicious Network Traffic Classificationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 7; 2025: 2; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentationcited by 39
  2. 2023How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attackscited by 18
  3. 2024Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Datacited by 11
  4. 2024TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-casescited by 10
  5. 2024How to Train your Antivirus: RL-based Hardening through the Problem-Spacecited by 3
  6. 2025On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defensescited by 3
  7. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  8. 2024TaeBench: Improving Quality of Toxic Adversarial Examplescited by 2
  9. 2023Constrained Adaptive Attacks: Realistic Evaluation of Adversarial Examples and Robust Training of Deep Neural Networks for Tabular Datacited by 1
  10. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  11. 2024What You See Is Not Always What You Get: Evaluating GPT's Comprehension of Source Codecited by 1
  12. 2024On the Effectiveness of Adversarial Training on Malware Classifierscited by 1
3 more
  1. 2025Insights on Adversarial Attacks for Tabular Machine Learning via a Systematic Literature Reviewcited by 0
  2. 2026REPLICANT: Learning Policies for Evading and Hardening Malware Detectorscited by 0
  3. 2026A GAN-Based Framework for Robust DDoS Attack Detectioncited by 0