mlsanityData to 7 Oct 2026

AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework

arXiv 2310.01818 ↗First posted 3 Oct 2023cs.LG cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

Robust Fine-Tuning (RFT) is a low-cost strategy to obtain adversarial robustness in downstream applications, without requiring a lot of computational resources and collecting significant amounts of data. This paper uncovers an issue with the existing RFT, where optimizing both adversarial and natural objectives through the feature extractor (FE) yields significantly divergent gradient directions. This divergence introduces instability in the optimization process, thereby hindering the attainment of adversarial robustness and rendering RFT highly sensitive to hyperparameters. To mitigate this issue, we propose a low-rank (LoRa) branch that disentangles RFT into two distinct components: optimizing natural objectives via the LoRa branch and adversarial objectives via the FE. Besides, we introduce heuristic strategies for automating the scheduling of the learning rate and the scalars of loss terms. Extensive empirical evaluations demonstrate that our proposed automated RFT disentangled via the LoRa branch (AutoLoRa) achieves new state-of-the-art results across a range of downstream tasks. AutoLoRa holds significant practical utility, as it automatically converts a pre-trained FE into an adversarially robust model for downstream tasks without the need for searching hyperparameters.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

33 of 41 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  9. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  10. 2013Describing Textures in the Wildcited by 2,110
  11. 2016Adversarial examples in the physical worldcited by 1,762
  12. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
21 more
  1. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  3. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  4. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  5. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  6. 2019Adversarial Examples Improve Image Recognitioncited by 283
  7. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  8. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  9. 2020Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learningcited by 139
  10. 2023One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuningcited by 84
  11. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 76
  12. 2019Adversarially robust transfer learningcited by 66
  13. 2021Reliable Adversarial Distillation with Unreliable Teacherscited by 55
  14. 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
  15. 2021Improved Fine-Tuning by Better Leveraging Pre-Training Datacited by 36
  16. 2021Adaptive Image Transformations for Transfer-based Adversarial Attackcited by 22
  17. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  18. 2023TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalizationcited by 18
  19. 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selectioncited by 14
  20. 2022Adversarial Contrastive Learning via Asymmetric InfoNCEcited by 13
  21. 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularizationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 2; 2026: 1.

9 papers.

  1. 2024FouRA: Fourier Low Rank Adaptationcited by 15
  2. 2023Initialization Matters for Adversarial Transfer Learningcited by 9
  3. 2024FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformerscited by 9
  4. 2025Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Modelscited by 9
  5. 2024Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-offcited by 5
  6. 2024Transfer Learning for Finetuning Large Language Modelscited by 5
  7. 2026IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoringcited by 5
  8. 2023Aggregate, Decompose, and Fine-Tune: A Simple Yet Effective Factor-Tuning Method for Vision Transformercited by 3
  9. 2025A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategycited by 1