FDA: Feature Disruptive Attack

09/10/2019
by   Aditya Ganeshan, et al.
0

Though Deep Neural Networks (DNN) show excellent performance across various computer vision tasks, several works show their vulnerability to adversarial samples, i.e., image samples with imperceptible noise engineered to manipulate the network's prediction. Adversarial sample generation methods range from simple to complex optimization techniques. Majority of these methods generate adversaries through optimization objectives that are tied to the pre-softmax or softmax output of the network. In this work we, (i) show the drawbacks of such attacks, (ii) propose two new evaluation metrics: Old Label New Rank (OLNR) and New Label Old Rank (NLOR) in order to quantify the extent of damage made by an attack, and (iii) propose a new adversarial attack FDA: Feature Disruptive Attack, to address the drawbacks of existing attacks. FDA works by generating image perturbation that disrupt features at each layer of the network and causes deep-features to be highly corrupt. This allows FDA adversaries to severely reduce the performance of deep networks. We experimentally validate that FDA generates stronger adversaries than other state-of-the-art methods for image classification, even in the presence of various defense measures. More importantly, we show that FDA disrupts feature-representation based tasks even without access to the task-specific network or methodology. Code available at: https://github.com/BardOfCodes/fda

READ FULL TEXT
research
04/26/2020

Towards Feature Space Adversarial Attack

We propose a new type of adversarial attack to Deep Neural Networks (DNN...
research
09/16/2021

KATANA: Simple Post-Training Robustness Using Test Time Augmentations

Although Deep Neural Networks (DNNs) achieve excellent performance on ma...
research
05/06/2022

Imperceptible Backdoor Attack: From Input Space to Feature Representation

Backdoor attacks are rapidly emerging threats to deep neural networks (D...
research
11/22/2019

Attack Agnostic Statistical Method for Adversarial Detection

Deep Learning based AI systems have shown great promise in various domai...
research
08/04/2022

Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classification

Vision Transformers (ViT) are competing to replace Convolutional Neural ...
research
07/11/2018

With Friends Like These, Who Needs Adversaries?

The vulnerability of deep image classification networks to adversarial a...
research
02/18/2023

RobustNLP: A Technique to Defend NLP Models Against Backdoor Attacks

As machine learning (ML) systems are being increasingly employed in the ...

Please sign up or login with your details

Forgot password? Click here to reset