# Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection

Source: [Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection](<https://www.sota2.com/research/paper/68fa70481e209131cea4a298>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:38:08.126Z

Authors: Hang Wang, Zhen Xiang, David J. Miller, George Kesidis

Published: 2023-08-08T22:47:39.000Z

## Abstract

Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify test-time triggers to the attacker's designated target class. Recent work shows that backdoor poisoning induces over-fitting (abnormally large activations) in the attacked model, which motivates a general, post-training clipping method for backdoor mitigation, i.e., with bounds on internal-layer activations learned using a small set of clean samples. We devise a new such approach, choosing the activation bounds to explicitly limit classification margins. This method gives superior performance against peer methods for CIFAR-10 image classification. We also show that this method has strong robustness against adaptive attacks, X2X attacks, and on different datasets. Finally, we demonstrate a method extension for test-time detection and correction based on the output differences between the original and activation-bounded networks. The code of our method is online available.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.04617>)

[PDF](<https://arxiv.org/pdf/2308.04617.pdf>)
