A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks

• URL: http://arxiv.org/abs/2411.10174v1
• Date: Fri, 15 Nov 2024 13:19:59 GMT
• Title: A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel Attacks
• Authors: Benoit Coqueret, Mathieu Carbone, Olivier Sentieys, Gabriel Zaid,
• Abstract summary: Protection of the intellectual property of Deep Neural Networks (DNNs) is still an issue and an emerging research field. Recent works have successfully extracted fully-connected DNNs using cryptanalytic methods in hard-label settings. We introduce a new end-to-end attack framework designed for model extraction of embedded DNNs with high fidelity.
• Score: 0.7499722271664147
• License:
• Abstract: During the past decade, Deep Neural Networks (DNNs) proved their value on a large variety of subjects. However despite their high value and public accessibility, the protection of the intellectual property of DNNs is still an issue and an emerging research field. Recent works have successfully extracted fully-connected DNNs using cryptanalytic methods in hard-label settings, proving that it was possible to copy a DNN with high fidelity, i.e., high similitude in the output predictions. However, the current cryptanalytic attacks cannot target complex, i.e., not fully connected, DNNs and are limited to special cases of neurons present in deep networks. In this work, we introduce a new end-to-end attack framework designed for model extraction of embedded DNNs with high fidelity. We describe a new black-box side-channel attack which splits the DNN in several linear parts for which we can perform cryptanalytic extraction and retrieve the weights in hard-label settings. With this method, we are able to adapt cryptanalytic extraction, for the first time, to non-fully connected DNNs, while maintaining a high fidelity. We validate our contributions by targeting several architectures implemented on a microcontroller unit, including a Multi-Layer Perceptron (MLP) of 1.7 million parameters and a shortened MobileNetv1. Our framework successfully extracts all of these DNNs with high fidelity (88.4% for the MobileNetv1 and 93.2% for the MLP). Furthermore, we use the stolen model to generate adversarial examples and achieve close to white-box performance on the victim's model (95.8% and 96.7% transfer rate).

Related papers

• Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networks [0.5849513679510833]
  A disadvantage of Deep Neural Networks (DNNs) is their vulnerability to adversarial attacks, as they can be fooled by adding slight perturbations to the inputs. This paper reports the results of devising a tiny DNN model, robust to adversarial black and white box attacks, trained with an automatic quantizationaware training framework.
  arXiv  Detail & Related papers  (2023-04-25T13:56:35Z)
• Robust and Lossless Fingerprinting of Deep Neural Networks via Pooled Membership Inference [17.881686153284267]
  Deep neural networks (DNNs) have already achieved great success in a lot of application areas and brought profound changes to our society. How to protect the intellectual property (IP) of DNNs against infringement is one of the most important yet very challenging topics. This paper proposes a novel technique called emphpooled membership inference (PMI) so as to protect the IP of the DNN models.
  arXiv  Detail & Related papers  (2022-09-09T04:06:29Z)
• Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks [55.531896312724555]
  Bayesian Networks (BNNs) are robust and adept at handling adversarial attacks by incorporating randomness. We create our BNN model, called BNN-DenseNet, by fusing Bayesian inference (i.e., variational Bayes) to the DenseNet architecture. An adversarially-trained BNN outperforms its non-Bayesian, adversarially-trained counterpart in most experiments.
  arXiv  Detail & Related papers  (2021-11-16T16:14:44Z)
• DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories [26.067920958354]
  One of the major threats to the privacy of Deep Neural Networks (DNNs) is model extraction attacks. Recent studies show hardware-based side channel attacks can reveal internal knowledge about DNN models (e.g., model architectures) We propose an advanced model extraction attack framework DeepSteal that effectively steals DNN weights with the aid of memory side-channel attack.
  arXiv  Detail & Related papers  (2021-11-08T16:55:45Z)
• Training Graph Neural Networks with 1000 Layers [133.84813995275988]
  We study reversible connections, group convolutions, weight tying, and equilibrium models to advance the memory and parameter efficiency of GNNs. To the best of our knowledge, RevGNN-Deep is the deepest GNN in the literature by one order of magnitude.
  arXiv  Detail & Related papers  (2021-06-14T15:03:00Z)
• HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks [16.388046449021466]
  We propose a novel solution for watermarking deep neural networks (DNNs) HufuNet is highly robust against model fine-tuning/pruning, kernels cutoff/supplement, functionality-equivalent attack, and fraudulent ownership claims.
  arXiv  Detail & Related papers  (2021-03-25T06:55:22Z)
• Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection [53.40245698216239]
  DSN (Deep Serial Number) is a watermarking algorithm designed specifically for deep neural networks (DNNs) Inspired by serial numbers in safeguarding conventional software IP, we propose the first implementation of serial number embedding within DNNs.
  arXiv  Detail & Related papers  (2020-11-17T21:42:40Z)
• Noise-Response Analysis of Deep Neural Networks Quantifies Robustness and Fingerprints Structural Malware [48.7072217216104]
  Deep neural networks (DNNs) have structural malware' (i.e., compromised weights and activation pathways) It is generally difficult to detect backdoors, and existing detection methods are computationally expensive and require extensive resources (e.g., access to the training data) Here, we propose a rapid feature-generation technique that quantifies the robustness of a DNN, fingerprints' its nonlinearity, and allows us to detect backdoors (if present) Our empirical results demonstrate that we can accurately detect backdoors with high confidence orders-of-magnitude faster than existing approaches (seconds versus
  arXiv  Detail & Related papers  (2020-07-31T23:52:58Z)
• DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips [29.34622626909906]
  We demonstrate the first hardware-based attack on quantized deep neural networks (DNNs) DeepHammer is able to successfully tamper DNN inference behavior at run-time within a few minutes. Our work highlights the need to incorporate security mechanisms in future deep learning system.
  arXiv  Detail & Related papers  (2020-03-30T18:51:59Z)
• Defending against Backdoor Attack on Deep Neural Networks [98.45955746226106]
  We study the so-called textitbackdoor attack, which injects a backdoor trigger to a small portion of training data. Experiments show that our method could effectively decrease the attack success rate, and also hold a high classification accuracy for clean images.
  arXiv  Detail & Related papers  (2020-02-26T02:03:00Z)
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets [83.12737997548645]
  Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) Use of skip connections allows easier generation of highly transferable adversarial examples. We conduct comprehensive transfer attacks against state-of-the-art DNNs including ResNets, DenseNets, Inceptions, Inception-ResNet, Squeeze-and-Excitation Network (SENet)
  arXiv  Detail & Related papers  (2020-02-14T12:09:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.