Defending Adversarial Attacks by Correcting logits

06/26/2019
by   Yifeng Li, et al.
2

Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning. While previous research verified that adversarial attacks are often fragile and can be defended via image-level processing, it remains unclear how high-level features are perturbed by such attacks. We investigate this issue from a new perspective, which purely relies on logits, the class scores before softmax, to detect and defend adversarial attacks. Our defender is a two-layer network trained on a mixed set of clean and perturbed logits, with the goal being recovering the original prediction. Upon a wide range of adversarial attacks, our simple approach shows promising results with relatively high accuracy in defense, and the defender can transfer across attackers with similar properties. More importantly, our defender can work in the scenarios that image data are unavailable, and enjoys high interpretability especially at the semantic level.

READ FULL TEXT

page 11

page 12

research
05/22/2023

Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation

State-of-the-art deep neural networks have proven to be highly powerful ...
research
02/25/2019

Adversarial attacks hidden in plain sight

Convolutional neural networks have been used to achieve a string of succ...
research
05/28/2021

Visualizing Representations of Adversarially Perturbed Inputs

It has been shown that deep learning models are vulnerable to adversaria...
research
05/26/2021

Intriguing Parameters of Structural Causal Models

In recent years there has been a lot of focus on adversarial attacks, es...
research
06/01/2020

Adversarial Attacks on Reinforcement Learning based Energy Management Systems of Extended Range Electric Delivery Vehicles

Adversarial examples are firstly investigated in the area of computer vi...
research
12/14/2019

Deep Poisoning Functions: Towards Robust Privacy-safe Image Data Sharing

As deep networks are applied to an ever-expanding set of computer vision...
research
06/11/2023

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework

With rich visual data, such as images, becoming readily associated with ...

Please sign up or login with your details

Forgot password? Click here to reset