Similarity of Neural Architectures using Adversarial Attack Transferability
- URL: http://arxiv.org/abs/2210.11407v4
- Date: Wed, 17 Jul 2024 15:10:22 GMT
- Title: Similarity of Neural Architectures using Adversarial Attack Transferability
- Authors: Jaehui Hwang, Dongyoon Han, Byeongho Heo, Song Park, Sanghyuk Chun, Jong-Seok Lee,
- Abstract summary: We design a quantitative and scalable similarity measure between neural architectures.
We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers.
Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
- Score: 47.66096554602005
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, many deep neural architectures have been developed for image classification. Whether they are similar or dissimilar and what factors contribute to their (dis)similarities remains curious. To address this question, we aim to design a quantitative and scalable similarity measure between neural architectures. We propose Similarity by Attack Transferability (SAT) from the observation that adversarial attack transferability contains information related to input gradients and decision boundaries widely used to understand model behaviors. We conduct a large-scale analysis on 69 state-of-the-art ImageNet classifiers using our proposed similarity function to answer the question. Moreover, we observe neural architecture-related phenomena using model similarity that model diversity can lead to better performance on model ensembles and knowledge distillation under specific conditions. Our results provide insights into why developing diverse neural architectures with distinct components is necessary.
Related papers
- Modularity in Transformers: Investigating Neuron Separability & Specialization [0.0]
Transformer models are increasingly prevalent in various applications, yet our understanding of their internal workings remains limited.
This paper investigates the modularity and task specialization of neurons within transformer architectures, focusing on both vision (ViT) and language (Mistral 7B) models.
Using a combination of selective pruning and MoEfication clustering techniques, we analyze the overlap and specialization of neurons across different tasks and data subsets.
arXiv Detail & Related papers (2024-08-30T14:35:01Z) - Characterization of topological structures in different neural network architectures [0.0]
We develop methods for analyzing representations from different architectures and check how one should use them to obtain valid results.
We applied these methods for ResNet, VGG19, and ViT architectures and found substantial differences along with some similarities.
arXiv Detail & Related papers (2024-07-08T18:02:18Z) - Multilayer Multiset Neuronal Networks -- MMNNs [55.2480439325792]
The present work describes multilayer multiset neuronal networks incorporating two or more layers of coincidence similarity neurons.
The work also explores the utilization of counter-prototype points, which are assigned to the image regions to be avoided.
arXiv Detail & Related papers (2023-08-28T12:55:13Z) - Neural Dependencies Emerging from Learning Massive Categories [94.77992221690742]
This work presents two astonishing findings on neural networks learned for large-scale image classification.
1) Given a well-trained model, the logits predicted for some category can be directly obtained by linearly combining the predictions of a few other categories.
2) Neural dependencies exist not only within a single model, but even between two independently learned models.
arXiv Detail & Related papers (2022-11-21T09:42:15Z) - DeepDC: Deep Distance Correlation as a Perceptual Image Quality
Evaluator [53.57431705309919]
ImageNet pre-trained deep neural networks (DNNs) show notable transferability for building effective image quality assessment (IQA) models.
We develop a novel full-reference IQA (FR-IQA) model based exclusively on pre-trained DNN features.
We conduct comprehensive experiments to demonstrate the superiority of the proposed quality model on five standard IQA datasets.
arXiv Detail & Related papers (2022-11-09T14:57:27Z) - Towards a Predictive Processing Implementation of the Common Model of
Cognition [79.63867412771461]
We describe an implementation of the common model of cognition grounded in neural generative coding and holographic associative memory.
The proposed system creates the groundwork for developing agents that learn continually from diverse tasks as well as model human performance at larger scales.
arXiv Detail & Related papers (2021-05-15T22:55:23Z) - Firearm Detection via Convolutional Neural Networks: Comparing a
Semantic Segmentation Model Against End-to-End Solutions [68.8204255655161]
Threat detection of weapons and aggressive behavior from live video can be used for rapid detection and prevention of potentially deadly incidents.
One way for achieving this is through the use of artificial intelligence and, in particular, machine learning for image analysis.
We compare a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation.
arXiv Detail & Related papers (2020-12-17T15:19:29Z) - Critically Examining the Claimed Value of Convolutions over User-Item
Embedding Maps for Recommender Systems [14.414055798999764]
In recent years, algorithm research in the area of recommender systems has shifted from matrix factorization techniques to neural approaches.
We show through analytical considerations and empirical evaluations that the claimed gains reported in the literature cannot be attributed to the ability of CNNs to model embedding correlations.
arXiv Detail & Related papers (2020-07-23T10:03:47Z) - Similarity Analysis of Contextual Word Representation Models [39.12749165544309]
We use existing and novel similarity measures to gauge the level of localization of information in the deep models.
The analysis reveals that models within the same family are more similar to one another, as may be expected.
Surprisingly, different architectures have rather similar representations, but different individual neurons.
arXiv Detail & Related papers (2020-05-03T19:48:15Z) - Architectural Resilience to Foreground-and-Background Adversarial Noise [0.0]
Adrial attacks in the form of imperceptible perturbations of normal images have been extensively studied.
We propose distinct model-agnostic benchmark perturbations of images to investigate resilience and robustness of different network architectures.
arXiv Detail & Related papers (2020-03-23T01:38:20Z)
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.