paper-with-me

Papers

Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering

2022-04-27 · Lukas Schulth, Christian Berghoff, Matthias Neu

Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There, we apply a $k$-means clustering algorithm on heatmaps produced by the state-of-the-art explainable AI method Layer-wise relevance propagation. The goal is to separate poisoned from un-poisoned data in the dataset. We compare this method with a similar method, called Activation Clustering, which also uses $k$-means clustering but applies it on the activation of certain hidden layers of the neural network as input. We test the performance of both approaches for standard backdoor poisoning attacks, label-consistent poisoning attacks and label-consistent poisoning attacks with reduced amplitude stickers. We show that Heatmap Clustering consistently performs better than Activation Clustering. However, when considering label-consistent poisoning attacks, the latter method also yields good detection performance.

📄 PDF Abstract BibTeX arXiv:2204.12848

Code (1)

lukasschulth/ma-detection-of-poisoning-attacks 공식 구현 pytorch

Tasks

Clustering

Methods 이 논문이 사용한 방법론

Heatmap 설명 없음

Similar Papers 제목 키워드 기반

Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study

2023-05-28 · Yiqi Zhong, Xianming Liu, Deming Zhai, Junjun Jiang 외

Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of increm…

Adversarial RobustnessBackdoor AttackData PoisoningIncremental Learning+1

PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks

2020-03-24 · Junfeng Guo, Ting Wang, Cong Liu

The black-box nature of deep neural networks (DNNs) facilitates attackers to manipulate the behavior of DNN through data poisoning. Being able to detect and mitigate poisoning attacks, typically categorized into backdoor…

Data Poisoning

PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments

2025-01-26 · Ajesh Koyatan Chathoth, Stephen Lee

The rapid expansion of connected devices has made them prime targets for cyberattacks. To address these threats, deep learning-based, data-driven intrusion detection systems (IDS) have emerged as powerful tools for detec…

backdoor defenseDeep LearningIntrusion Detection

Detecting Backdoors in Deep Text Classifiers

2022-10-11 · You Guo, Jun Wang, Trevor Cohn

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attach…

Data Poisoningtext-classificationText Classification

Detecting Backdoor Samples in Contrastive Language Image Pretraining

2025-02-03 · Hanxun Huang, Sarah Erfani, Yige Li, Xingjun Ma 외

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of…