paper-with-me

홈 › Papers

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

2023-06-14 · Ziqiang Li, Hong Sun, Pengfei Xia, Heng Li, Beihao Xia, Yi Wu, Bin Li

Recent deep neural networks (DNNs) have came to rely on vast amounts of training data, providing an opportunity for malicious attackers to exploit and contaminate the data to carry out backdoor attacks. However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data. In this paper, we introduce a more realistic attack scenario where victims collect data from multiple sources, and attackers cannot access the complete training data. We refer to this scenario as data-constrained backdoor attacks. In such cases, previous attack methods suffer from severe efficiency degradation due to the entanglement between benign and poisoning features during the backdoor injection process. To tackle this problem, we introduce three CLIP-based technologies from two distinct streams: Clean Feature Suppression and Poisoning Feature Augmentation.effective solution for data-constrained backdoor attacks. The results demonstrate remarkable improvements, with some settings achieving over 100% improvement compared to existing attacks in data-constrained scenarios. Code is available at https://github.com/sunh1113/Efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios

📄 PDF Abstract BibTeX arXiv:2306.08386

Code (1)

sunh1113/efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios 공식 구현 pytorch

Tasks

Backdoor Attack

Similar Papers 제목 키워드 기반

Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras

2024-11-05 · Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta

While security vulnerabilities in traditional Deep Neural Networks (DNNs) have been extensively studied, the susceptibility of Spiking Neural Networks (SNNs) to adversarial attacks remains mostly underexplored. Until now…

Backdoor Attack

Clean-Label Backdoor Attacks on Video Recognition Models

2020-03-06 · CVPR 2020 6 · Shihao Zhao, Xingjun Ma, Xiang Zheng, James Bailey 외

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a pa…

Backdoor Attackbackdoor defenseimage-classificationImage Classification+1

Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios

2023-06-13 · Haochen Mei, Gaolei Li, Jun Wu, Longfei Zheng

Federated learning (FL) naturally faces the problem of data heterogeneity in real-world scenarios, but this is often overlooked by studies on FL security and privacy. On the one hand, the effectiveness of backdoor attack…

Backdoor AttackFederated Learning

Robust Backdoor Attacks against Deep Neural Networks in Real Physical World

2021-04-15 · Mingfu Xue, Can He, Shichang Sun, Jian Wang 외

Deep neural networks (DNN) have been widely deployed in various applications. However, many researches indicated that DNN is vulnerable to backdoor attacks. The attacker can create a hidden backdoor in target DNN model, …

Backdoor AttackFace Recognition

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

2024-04-30 · CVPR 2024 1 · Wen Yin, Jian Lou, Pan Zhou, Yulai Xie 외

Backdoor attacks have been well-studied in visible light object detection (VLOD) in recent years. However, VLOD can not effectively work in dark and temperature-sensitive scenarios. Instead, thermal infrared object detec…

Objectobject-detectionObject Detection