mlsanityData to 7 Oct 2026

Robustness Reprogramming for Representation Learning

arXiv 2410.04577 ↗First posted 6 Oct 2024cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without altering its parameters? To explore this, we revisit the core feature transformation mechanism in representation learning and propose a novel non-linear robust pattern matching technique as a robust alternative. Furthermore, we introduce three model reprogramming paradigms to offer flexible control of robustness under different efficiency requirements. Comprehensive experiments and ablation studies across diverse learning models ranging from basic linear model and MLPs to shallow and modern deep ConvNets demonstrate the effectiveness of our approaches. This work not only opens a promising and orthogonal direction for improving adversarial defenses in deep learning beyond existing methods but also provides new insights into designing more resilient AI systems with robust statistics.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 6 Oct 2024.

Builds on

34 of 43 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  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
22 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  2. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  3. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  4. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  5. 2022Diffusion Models for Adversarial Purificationcited by 469
  6. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  7. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  8. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 290
  9. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  10. 2017Detecting Adversarial Samples from Artifactscited by 244
  11. 2021Improving Robustness using Generated Datacited by 233
  12. 2017On Detecting Adversarial Perturbationscited by 232
  13. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  14. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  15. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  16. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  17. 2021Adversarial purification with Score-based generative modelscited by 132
  18. 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
  19. 2019On Robustness of Neural Ordinary Differential Equationscited by 83
  20. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  21. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  22. 2023WAT: Improve the Worst-class Robustness in Adversarial Trainingcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2025Boosting Adversarial Robustness and Generalization with Dictionary Structurecited by 1
  2. 2026Stratified Consistency Distillation for Natural Language Formalizationcited by 1
  3. 2024Leveraging Scene Geometry and Depth Information for Robust Image Derainingcited by 0
  4. 2026Towards One-for-All Robustness Across a Continuum of Threat Levelscited by 0