paper-with-me

홈 › Papers

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks

2024-08-07 · Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa

Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply that increasing the diversity of model outputs contributes to improving the attack performance. This study focuses on the Auto Conjugate Gradient (ACG) attack, which is inspired by the conjugate gradient method and has a high diversification performance. We hypothesized that increasing the distance between two consecutive search points would enhance the output diversity. To test our hypothesis, we propose Rescaling-ACG (ReACG), which automatically modifies the two components that significantly affect the distance between two consecutive search points, including the search direction and step size. ReACG showed higher attack performance than that of ACG, and is particularly effective for ImageNet models with several classification classes. Experimental results show that the distance between two consecutive search points enhances the output diversity and may help develop new potent attacks. The code is available at \url{https://github.com/yamamura-k/ReACG}

📄 PDF Abstract BibTeX arXiv:2408.03972

Code (1)

yamamura-k/reacg 공식 구현 pytorch

Tasks

Diversity

Similar Papers 제목 키워드 기반

Diversified Adversarial Attacks based on Conjugate Gradient Method

2022-06-20 · Keiichiro Yamamura, Haruki Sato, Nariaki Tateiwa, Nozomi Hata 외

Deep learning models are vulnerable to adversarial examples, and adversarial attacks used to generate such examples have attracted considerable research interest. Although existing methods based on the steepest descent h…

Diversity

Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training

2018-12-07 · Saurabh Adya, Vinay Palakkode, Oncel Tuzel

Nonlinear conjugate gradient (NLCG) based optimizers have shown superior loss convergence properties compared to gradient descent based optimizers for traditional optimization problems. However, in Deep Neural Network (D…

16kGeneral Classification

Conjugate Gradients for Kernel Machines

2019-11-14 · Simon Bartels, Philipp Hennig

Regularized least-squares (kernel-ridge / Gaussian process) regression is a fundamental algorithm of statistics and machine learning. Because generic algorithms for the exact solution have cubic complexity in the number …

BIG-bench Machine Learningregression

Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW

2025-07-01 · Di Zhang, Yihang Zhang arxiv

Stochastic gradient-based descent (SGD), have long been central to training large language models (LLMs). However, their effectiveness is increasingly being questioned, particularly in large-scale applications where empi…

Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models

2017-03-13 · Mohammad Emtiyaz Khan, Wu Lin

Variational inference is computationally challenging in models that contain both conjugate and non-conjugate terms. Methods specifically designed for conjugate models, even though computationally efficient, find it diffi…

Variational Inference