mlsanityData to 7 Oct 2026

MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework

arXiv 2501.07251 ↗First posted 13 Jan 2025cs.LG cs.AI cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Crafting adversarial examples is crucial for evaluating and enhancing the robustness of Deep Neural Networks (DNNs), presenting a challenge equivalent to maximizing a non-differentiable 0-1 loss function. However, existing single objective methods, namely adversarial attacks focus on a surrogate loss function, do not fully harness the benefits of engaging multiple loss functions, as a result of insufficient understanding of their synergistic and conflicting nature. To overcome these limitations, we propose the Multi-Objective Set-based Attack (MOS Attack), a novel adversarial attack framework leveraging multiple loss functions and automatically uncovering their interrelations. The MOS Attack adopts a set-based multi-objective optimization strategy, enabling the incorporation of numerous loss functions without additional parameters. It also automatically mines synergistic patterns among various losses, facilitating the generation of potent adversarial attacks with fewer objectives. Extensive experiments have shown that our MOS Attack outperforms single-objective attacks. Furthermore, by harnessing the identified synergistic patterns, MOS Attack continues to show superior results with a reduced number of loss functions. Our code is available at https://github.com/pgg3/MOS-Attack.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 53 references that are in the map. First posted on arXiv 13 Jan 2025.

Builds on

38 of 53 references.

References · 38

  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. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  10. 2017Dynamic Routing Between Capsulescited by 689
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
26 more
  1. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  2. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  3. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  4. 2021Improving Robustness using Generated Datacited by 233
  5. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  6. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  7. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  8. 2020Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuningcited by 152
  9. 2019Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Drivingcited by 151
  10. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  11. 2020Adversarial Robustness on In- and Out-Distribution Improves Explainabilitycited by 73
  12. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 73
  13. 2020Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 61
  14. 2024Smooth Tchebycheff Scalarization for Multi-Objective Optimizationcited by 50
  15. 2019An Alternative Surrogate Loss for PGD-based Adversarial Testingcited by 45
  16. 2021AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Taskscited by 19
  17. 2024Few for Many: Tchebycheff Set Scalarization for Many-Objective Optimizationcited by 15
  18. 2022Diversified Adversarial Attacks based on Conjugate Gradient Methodcited by 11
  19. 2019Adversarial Example Generation using Evolutionary Multi-objective Optimizationcited by 9
  20. 2024L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attackscited by 8
  21. 2021Effective and Imperceptible Adversarial Textual Attack via Multi-objectivizationcited by 5
  22. 2021Effective Universal Unrestricted Adversarial Attacks using a MOE Approachcited by 4
  23. 2021Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Searchcited by 3
  24. 2024Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolumecited by 3
  25. 2024A Multi-task Adversarial Attack Against Face Authenticationcited by 3
  26. 2022Alternating Objectives Generates Stronger PGD-Based Adversarial Attackscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Few-for-Many Personalized Federated Learningcited by 0