Mitigating Backdoor Attack Via Prerequisite Transformation

by   Han Gao, et al.

In recent years, with the successful application of DNN in fields such as NLP and CV, its security has also received widespread attention. (Author) proposed the method of backdoor attack in Badnet. Switch implanted backdoor into the model by poisoning the training samples. The model with backdoor did not exhibit any abnormalities on the normal validation sample set, but in the input with trigger, they were mistakenly classified as the attacker's designated category or randomly classified as a different category from the ground truth, This attack method seriously threatens the normal application of DNN in real life, such as autonomous driving, object detection, etc.This article proposes a new method to combat backdoor attacks. We refer to the features in the area covered by the trigger as trigger features, and the remaining areas as normal features. By introducing prerequisite calculation conditions during the training process, these conditions have little impact on normal features and trigger features, and can complete the training of a standard backdoor model. The model trained under these prerequisite calculation conditions can, In the verification set D'val with the same premise calculation conditions, the performance is consistent with that of the ordinary backdoor model. However, in the verification set Dval without the premise calculation conditions, the verification accuracy decreases very little (7 rate (ASR) decreases from 90 Transformation(PT).


Backdoor Attack against Object Detection with Clean Annotation

Deep neural networks (DNNs) have shown unprecedented success in object d...

A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verification

We introduce a new attack against face verification systems based on Dee...

A new approach to Statistical analysis of election results

In this paper, a new method of detection of election fraud is proposed. ...

Transformation-Equivariant 3D Object Detection for Autonomous Driving

3D object detection received increasing attention in autonomous driving ...

SATBA: An Invisible Backdoor Attack Based On Spatial Attention

As a new realm of AI security, backdoor attack has drew growing attentio...

Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems

We show that by controlling parts of a physical environment in which a p...

Please sign up or login with your details

Forgot password? Click here to reset