# Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking

Source: [Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking](<https://www.sota2.com/research/paper/68fa758e1e209131cea68996>)

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

Data updated: 2025-10-26T03:36:51.485Z

Authors: Shengsheng Qian, Dizhan Xue, Yifei Wang, Shengjie Zhang, Huaiwen Zhang, Changsheng Xu

Published: 2023-12-13T08:01:15.000Z

## Abstract

Self-Supervised Learning (SSL) is an effective paradigm for learning representations from unlabeled data, such as text, images, and videos. However, researchers have recently found that SSL is vulnerable to backdoor attacks. The attacker can embed hidden SSL backdoors via a few poisoned examples in the training dataset and maliciously manipulate the behavior of downstream models. To defend against SSL backdoor attacks, a feasible route is to detect and remove the poisonous samples in the training set. However, the existing SSL backdoor defense method fails to detect the poisonous samples precisely. In this paper, we propose to erase the SSL backdoor by cluster activation masking and propose a novel PoisonCAM method. After obtaining the threat model trained on the poisoned dataset, our method can precisely detect poisonous samples based on the assumption that masking the backdoor trigger can effectively change the activation of a downstream clustering model. In experiments, our PoisonCAM achieves 96\\% accuracy for backdoor trigger detection compared to 3\\% of the state-of-the-art method on poisoned ImageNet-100. Moreover, our proposed PoisonCAM significantly improves the performance of the trained SSL model under backdoor attacks compared to the state-of-the-art method. Our code, data, and trained models will be open once this paper is accepted.

## 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/2312.07955>)

[PDF](<https://arxiv.org/pdf/2312.07955.pdf>)
