mlsanityData to 7 Oct 2026

Towards Adversarial Robustness via Transductive Learning

arXiv 2106.08387 ↗First posted 15 Jun 2021cs.LG cs.CRcited by 2

Not on the map. Why?

Abstract (arXiv)

There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain" the model based on test time input via transductive learning; and theoretically, attacking these defenses boils down to bilevel optimization, which seems to raise the difficulty for adaptive attacks. In this paper, we first formalize and analyze modeling aspects of transductive robustness. Then, we propose the principle of attacking model space for solving bilevel attack objectives, and present an instantiation of the principle which breaks previous transductive defenses. These attacks thus point to significant difficulties in the use of transductive learning to improve adversarial robustness. To this end, we present new theoretical and empirical evidence in support of the utility of transductive learning.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

24 of 34 references.

References · 24

  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. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  8. 2016Adversarial examples in the physical worldcited by 1,762
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
12 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  3. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  4. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  5. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  6. 2018Adversarially Robust Generalization Requires More Datacited by 318
  7. 2017The Space of Transferable Adversarial Examplescited by 156
  8. 2014Domain-Adversarial Neural Networkscited by 78
  9. 2018Stochastic Hyperparameter Optimization through Hypernetworkscited by 72
  10. 2020Estimating Generalization under Distribution Shifts via Domain-Invariant Representationscited by 56
  11. 2020Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examplescited by 44
  12. 2019A Research Agenda: Dynamic Models to Defend Against Correlated Attackscited by 18

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 1.

2 papers.

  1. 2021Transductive Robust Learning Guaranteescited by 10
  2. 2023Computational Asymmetries in Robust Classificationcited by 2