On the Steganographic Capacity of Selected Learning Models

• URL: http://arxiv.org/abs/2308.15502v1
• Date: Tue, 29 Aug 2023 10:41:34 GMT
• Title: On the Steganographic Capacity of Selected Learning Models
• Authors: Rishit Agrawal and Kelvin Jou and Tanush Obili and Daksh Parikh and Samarth Prajapati and Yash Seth and Charan Sridhar and Nathan Zhang and Mark Stamp
• Abstract summary: We consider the question of the steganographic capacity of learning models. For a wide range of models, we determine the number of low-order bits that can be overwritten. Of the models tested, the steganographic capacity ranges from 7.04 KB for our LR experiments, to 44.74 MB for InceptionV3.
• Score: 1.0640226829362012
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning and deep learning models are potential vectors for various attack scenarios. For example, previous research has shown that malware can be hidden in deep learning models. Hiding information in a learning model can be viewed as a form of steganography. In this research, we consider the general question of the steganographic capacity of learning models. Specifically, for a wide range of models, we determine the number of low-order bits of the trained parameters that can be overwritten, without adversely affecting model performance. For each model considered, we graph the accuracy as a function of the number of low-order bits that have been overwritten, and for selected models, we also analyze the steganographic capacity of individual layers. The models that we test include the classic machine learning techniques of Linear Regression (LR) and Support Vector Machine (SVM); the popular general deep learning models of Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN); the highly-successful Recurrent Neural Network (RNN) architecture of Long Short-Term Memory (LSTM); the pre-trained transfer learning-based models VGG16, DenseNet121, InceptionV3, and Xception; and, finally, an Auxiliary Classifier Generative Adversarial Network (ACGAN). In all cases, we find that a majority of the bits of each trained parameter can be overwritten before the accuracy degrades. Of the models tested, the steganographic capacity ranges from 7.04 KB for our LR experiments, to 44.74 MB for InceptionV3. We discuss the implications of our results and consider possible avenues for further research.

Related papers

• Variational autoencoder-based neural network model compression [4.992476489874941]
  Variational Autoencoders (VAEs), as a form of deep generative model, have been widely used in recent years. This paper aims to explore neural network model compression method based on VAE.
  arXiv  Detail & Related papers  (2024-08-25T09:06:22Z)
• Towards Scalable and Versatile Weight Space Learning [51.78426981947659]
  This paper introduces the SANE approach to weight-space learning. Our method extends the idea of hyper-representations towards sequential processing of subsets of neural network weights.
  arXiv  Detail & Related papers  (2024-06-14T13:12:07Z)
• Steganographic Capacity of Deep Learning Models [12.974139332068491]
  We consider the steganographic capacity of several learning models. We train a Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Transformer model on a challenging malware classification problem. We find that the steganographic capacity of the learning models tested is surprisingly high, and that in each case, there is a clear threshold after which model performance rapidly degrades.
  arXiv  Detail & Related papers  (2023-06-25T13:43:35Z)
• LowDINO -- A Low Parameter Self Supervised Learning Model [0.0]
  This research aims to explore the possibility of designing a neural network architecture that allows for small networks to adopt the properties of huge networks. Previous studies have shown that using convolutional neural networks (ConvNets) can provide inherent inductive bias. To reduce the number of parameters, attention mechanisms are utilized through the usage of MobileViT blocks.
  arXiv  Detail & Related papers  (2023-05-28T18:34:59Z)
• Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning [19.220263739291685]
  Speech emotion recognition (SER) has been a popular research topic in human-computer interaction (HCI) We propose a neural structured learning (NSL) framework through building synthesized graphs. Our experiments demonstrate that training a lightweight SER model on the target dataset with speech samples and graphs can not only produce small SER models, but also enhance the model performance.
  arXiv  Detail & Related papers  (2022-10-26T18:38:42Z)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• Part-Based Models Improve Adversarial Robustness [57.699029966800644]
  We show that combining human prior knowledge with end-to-end learning can improve the robustness of deep neural networks. Our model combines a part segmentation model with a tiny classifier and is trained end-to-end to simultaneously segment objects into parts. Our experiments indicate that these models also reduce texture bias and yield better robustness against common corruptions and spurious correlations.
  arXiv  Detail & Related papers  (2022-09-15T15:41:47Z)
• Classification of EEG Motor Imagery Using Deep Learning for Brain-Computer Interface Systems [79.58173794910631]
  A trained T1 class Convolutional Neural Network (CNN) model will be used to examine its ability to successfully identify motor imagery. In theory, and if the model has been trained accurately, it should be able to identify a class and label it accordingly. The CNN model will then be restored and used to try and identify the same class of motor imagery data using much smaller sampled data.
  arXiv  Detail & Related papers  (2022-05-31T17:09:46Z)
• A Distillation Learning Model of Adaptive Structural Deep Belief Network for AffectNet: Facial Expression Image Database [0.0]
  We have developed the adaptive structure learning method of Deep Belief Network (DBN) In this paper, our model is applied to a facial expression image data set, AffectNet. The classification accuracy was improved from 78.4% to 91.3% by the proposed method.
  arXiv  Detail & Related papers  (2021-10-25T08:01:36Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms [58.684954492439424]
  We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data. The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
  arXiv  Detail & Related papers  (2021-04-11T12:14:04Z)

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.