Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose key-based defense model proliferation by leveraging pre-trained models and utilizing recent efficient fine-tuning techniques on ImageNet-1k classification. First, we stress that deploying key-based models on edge devices is feasible with the latest model deployment advancements, such as Apple CoreML, although the mainstream enterprise edge artificial intelligence (Edge AI) has been focused on the Cloud. Then, we point out that the previous key-based defense on on-device image classification is impractical for two reasons: (1) training many classifiers from scratch is not feasible, and (2) key-based defenses still need to be thoroughly tested on large datasets like ImageNet. To this end, we propose to leverage pre-trained models and utilize efficient fine-tuning techniques to proliferate key-based models even on limited computing resources. Experiments were carried out on the ImageNet-1k dataset using adaptive and non-adaptive attacks. The results show that our proposed fine-tuned key-based models achieve a superior classification accuracy (more than 10% increase) compared to the previous key-based models on classifying clean and adversarial examples.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 61 of its 77 references that are in the map. First posted on arXiv 28 Nov 2023.
Builds on
61 of 77 references.
References · 61
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2013Intriguing properties of neural networkscited by 5,155
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2022A ConvNet for the 2020scited by 3,579
- 2016Adversarial examples in the physical worldcited by 1,769
38 more
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2014How transferable are features in deep neural networks?cited by 1,225
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2020Fast is better than free: Revisiting adversarial trainingcited by 727
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
- 2019Adversarial Training for Free!cited by 643
- 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
- 2021ImageNet-21K Pretraining for the Massescited by 613
- 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
- 2017Countering Adversarial Images using Input Transformationscited by 520
- 2017Adversarial Patchcited by 517
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2017Mitigating Adversarial Effects Through Randomizationcited by 383
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2018Certified Defenses against Adversarial Examplescited by 306
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 185
- 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 163
- 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
- 2017Generative Adversarial Perturbationscited by 153
- 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
- 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
- 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
- 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
- 2022Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspectivecited by 57
- 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 43
- 2018Unrestricted Adversarial Examplescited by 40
- 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
50 most cited of 61 All 61 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.