paper-with-me

Papers

Stochastic Combinatorial Ensembles for Defending Against Adversarial Examples

2018-08-20 · George A. Adam, Petr Smirnov, David Duvenaud, Benjamin Haibe-Kains, Anna Goldenberg

Many deep learning algorithms can be easily fooled with simple adversarial examples. To address the limitations of existing defenses, we devised a probabilistic framework that can generate an exponentially large ensemble of models from a single model with just a linear cost. This framework takes advantage of neural network depth and stochastically decides whether or not to insert noise removal operators such as VAEs between layers. We show empirically the important role that model gradients have when it comes to determining transferability of adversarial examples, and take advantage of this result to demonstrate that it is possible to train models with limited adversarial attack transferability. Additionally, we propose a detection method based on metric learning in order to detect adversarial examples that have no hope of being cleaned of maliciously engineered noise.

📄 PDF Abstract BibTeX arXiv:1808.06645

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackMetric Learning

Similar Papers 제목 키워드 기반

Defending Textual Neural Networks against Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the…

SHIELD: Defending Textual Neural Networks against Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the…

SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher

2020-11-17 · ACL 2022 5 · Thai Le, Noseong Park, Dongwon Lee

Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the…

Adversarial Robustness

Defending against black-box adversarial attacks with gradient-free trained sign activation neural networks

2021-01-01 · Yunzhe Xue, Meiyan Xie, Zhibo Yang, Usman Roshan

Binary neural networks have been shown to be more adversarially robust than full-precision networks but their improvements are marginal. We propose an ensemble of sign activation neural networks trained with a novel grad…

Adversarial Defense

$n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers

2019-12-19 · Mahmood Sharif, Lujo Bauer, Michael K. Reiter

This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version program…

General Classification