mlsanityData to 7 Oct 2026

PredCoin: Defense against Query-based Hard-label Attack

arXiv 2102.02923 ↗First posted 4 Feb 2021cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new class of query-based hard-label (QBHL) black-box attacks pose a significant threat to real-world applications (e.g., Google Cloud, Tencent API). Till now, there has been no generalizable and practical approach proposed to defend against such attacks. This paper proposes and evaluates PredCoin, a practical and generalizable method for providing robustness against QBHL attacks. PredCoin poisons the gradient estimation step, an essential component of most QBHL attacks. PredCoin successfully identifies gradient estimation queries crafted by an attacker and introduces uncertainty to the output. Extensive experiments show that PredCoin successfully defends against four state-of-the-art QBHL attacks across various settings and tasks while preserving the target model's overall accuracy. PredCoin is also shown to be robust and effective against several defense-aware attacks, which may have full knowledge regarding the internal mechanisms of PredCoin.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 4 Feb 2021.

Builds on

34 of 58 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  9. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  10. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
  11. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  12. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
22 more
  1. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  2. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  3. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  4. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  5. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  6. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
  7. 2019Sign-OPT: A Query-Efficient Hard-label Adversarial Attackcited by 118
  8. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  9. 2017Comparative Study of CNN and RNN for Natural Language Processingcited by 81
  10. 2015A Primer on Neural Network Models for Natural Language Processingcited by 75
  11. 2019PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Drivingcited by 72
  12. 2017Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Carcited by 65
  13. 2017Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detectioncited by 65
  14. 2018DeepBugs: A Learning Approach to Name-based Bug Detectioncited by 65
  15. 2018Fast Gradient Attack on Network Embeddingcited by 65
  16. 2017Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classificationcited by 56
  17. 2019Stateful Detection of Black-Box Adversarial Attackscited by 55
  18. 2017Adversarial and Clean Data Are Not Twinscited by 52
  19. 2018DeepBillboard: Systematic Physical-World Testing of Autonomous Driving Systemscited by 50
  20. 2016Adversarial Perturbations Against Deep Neural Networks for Malware Classificationcited by 42
  21. 2018Neural Machine Translation Inspired Binary Code Similarity Comparison beyond Function Pairscited by 25
  22. 2014DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detectioncited by 19

Built on by

Not cited yet.