paper-with-me

홈 › Papers

Global Adversarial Attacks for Assessing Deep Learning Robustness

2019-06-19 · Hanbin Hu, Mit Shah, Jianhua Z. Huang, Peng Li

It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing adversarial attacks, we present a new type of global adversarial attacks for assessing global DNN robustness. More specifically, we propose a novel concept of global adversarial example pairs in which each pair of two examples are close to each other but have different class labels predicted by the DNN. We further propose two families of global attack methods and show that our methods are able to generate diverse and intriguing adversarial example pairs at locations far from the training or testing data. Moreover, we demonstrate that DNNs hardened using the strong projected gradient descent (PGD) based (local) adversarial training are vulnerable to the proposed global adversarial example pairs, suggesting that global robustness must be considered while training robust deep learning networks.

📄 PDF Abstract BibTeX arXiv:1906.07920

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Similar Papers 제목 키워드 기반

Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification

2020-02-07 · Meet P. Vadera, Satya Narayan Shukla, Brian Jalaian, Benjamin M. Marlin

In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations. We chara…

Adversarial RobustnessGeneral Classification

How to compare adversarial robustness of classifiers from a global perspective

2020-04-22 · Niklas Risse, Christina Göpfert, Jan Philip Göpfert

Adversarial robustness of machine learning models has attracted considerable attention over recent years. Adversarial attacks undermine the reliability of and trust in machine learning models, but the construction of mor…

Adversarial RobustnessBIG-bench Machine Learning

Improving Model Robustness with Latent Distribution Locally and Globally

2021-07-08 · Zhuang Qian, Shufei Zhang, Kaizhu Huang, Qiufeng Wang 외

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial t…

Adversarial Robustness

A Hierarchical Assessment of Adversarial Severity

2021-08-26 · Guillaume Jeanneret, Juan C Perez, Pablo Arbelaez

Adversarial Robustness is a growing field that evidences the brittleness of neural networks. Although the literature on adversarial robustness is vast, a dimension is missing in these studies: assessing how severe the mi…

Adversarial Robustness

KGPA: Robustness Evaluation for Large Language Models via Cross-Domain Knowledge Graphs

2024-06-16 · Aihua Pei, Zehua Yang, Shunan Zhu, Ruoxi Cheng 외

Existing frameworks for assessing robustness of large language models (LLMs) overly depend on specific benchmarks, increasing costs and failing to evaluate performance of LLMs in professional domains due to dataset limit…

Adversarial AttackAdversarial RobustnessKnowledge Graphs