首页/论文/2007.14748

arXiv 2007.147482020-07cs.CR

Towards a Backdoorless Network Architecture Based on Remote Attestation and Backdoor Inspection

Takayuki Sasaki, Yusuke Shimada

英文摘要：

To keep a system secure, all devices in the system need to be benign. To avoid malicious and/or compromised devices, network access control such as authentication using a credential and remote attestation based on trusted hardware has been used. These techniques ensure the authenticity and integrity of the devices, but do not mitigate risks of a backdoor embedded in the devices by the developer. To tackle this problem, we propose a novel architecture that integrates remote attestation and backdoor inspection. Specifically, the backdoor inspection result is stored in a server and the verifier retrieves and checks the backdoor inspection result when the remote attestation is performed. Moreover, we discuss issues to deploy the proposed architecture to the real world.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

EmInspector：通过嵌入检查对抗联邦自监督学习中的后门攻击

EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection

本文针对联邦自监督学习（FSSL）中的后门攻击，提出EmInspector方法，通过检查本地模型嵌入空间检测恶意客户端，利用少量检查图像评估嵌入相似性，有效缓解各类对手设置下的后门攻击。

2024-05-21cs.CRcs.LG

DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection

Technical University of Darmstadt（达姆施塔特工业大学）

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These attacks inject a backdoor into the resulting model that allows adversary-controlled inputs to be misclassified. Existing countermeasures against backdoor attacks are inefficient and often merely aim to exclude deviating models from the aggregation. However, this approach also removes benign models of clients with deviating data distributions, causing the aggregat…

2022-01-03cs.CRcs.LG

SGBA: A Stealthy Scapegoat Backdoor Attack against Deep Neural Networks

Outsourced deep neural networks have been demonstrated to suffer from patch-based trojan attacks, in which an adversary poisons the training sets to inject a backdoor in the obtained model so that regular inputs can be still labeled correctly while those carrying a specific trigger are falsely given a target label. Due to the severity of such attacks, many backdoor detection and containment systems have recently, been proposed for deep neural networks. One major category among them are various model inspection schemes, which hope to detect backdoors before deploying models from non-trusted thi…

2022-05-16cs.CR

通过方向对齐检测识别联邦学习中的后门攻击

Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection

University of Nevada, Reno（内华达大学雷诺分校）

针对联邦学习易受后门攻击且现有防御忽略更新方向不一致的问题，提出AlignIns防御方法，通过方向对齐检测过滤恶意更新，理论与实验均验证其鲁棒性优于现有方法。

2025-03-18cs.CRcs.DCcs.LG

WaNet -- Imperceptible Warping-based Backdoor Attack

VinAI Research（VinAI研究院）；Hanoi University of Science and Technology（河内科技大学）；VinUniversity

With the thriving of deep learning and the widespread practice of using pre-trained networks, backdoor attacks have become an increasing security threat drawing many research interests in recent years. A third-party model can be poisoned in training to work well in normal conditions but behave maliciously when a trigger pattern appears. However, the existing backdoor attacks are all built on noise perturbation triggers, making them noticeable to humans. In this paper, we instead propose using warping-based triggers. The proposed backdoor outperforms the previous methods in a human inspection t…

2021-03-04cs.CRcs.CV

针对深度神经网络的频域不可见后门攻击

Towards Invisible Backdoor Attacks in the Frequency Domain against Deep Neural Networks

本文提出一种基于离散傅里叶变换的频域后门攻击方法，通过在图像频域中添加隐蔽触发器，在保持攻击成功率和干净样本准确率的同时，实现欺骗人类检查和DNN模型的目的。

2023-05-10cs.CR

更多相关论文收起更多论文

基于模型架构修改的不可见触发器后门攻击

Backdoor Attack with Invisible Triggers Based on Model Architecture Modification

School of Cyber Science and Engineering（网络科学与工程学院）

本文提出一种将后门嵌入模型架构并能生成不可见触发器的新型后门攻击方法，通过修改并重新分发预训练模型实施攻击，实验证明其有效且触发器难以被人工和工具检测。

2025-09-23cs.AIcs.CR

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland（马里兰大学）；New York University（纽约大学）

As the curation of data for machine learning becomes increasingly automated, dataset tampering is a mounting threat. Backdoor attackers tamper with training data to embed a vulnerability in models that are trained on that data. This vulnerability is then activated at inference time by placing a "trigger" into the model's input. Typical backdoor attacks insert the trigger directly into the training data, although the presence of such an attack may be visible upon inspection. In contrast, the Hidden Trigger Backdoor Attack achieves poisoning without placing a trigger into the training data at al…

2022-10-13cs.CRcs.CVcs.LG

Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization

Shanghai Jiao Tong University（上海交通大学）；The University of Adelaide（阿德莱德大学）；The University of New South Wales（新南威尔士大学）；Data61 CSIRO（澳大利亚联邦科学与工业研究组织 Data61）；Shanghai Institute for Advanced Communication and Data Science（上海先进通信与数据科学研究院）；Shanghai University（上海大学）

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this paper, we create covert and scattered triggers for backdoor attacks, invisible backdoors, where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steg…

2020-08-31cs.CRcs.CVcs.LG

PiDAn：一种用于深度神经网络后门攻击检测与缓解的相干性优化方法

PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

New York University（纽约大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）；Tandon School of Engineering（坦登工程学院）

本文提出基于相干性优化的PiDAn算法，通过学习样本级权重向量区分真实与污染数据表征，在GTSRB和ILSVRC2012数据集上有效检测并缓解深度神经网络后门攻击。

2022-03-26cs.CRcs.LG

针对深度学习商业框架的量化后门

Quantization Backdoors to Deep Learning Commercial Frameworks

The University of Adelaide（阿德莱德大学）；Data61, CSIRO（联邦科学与工业研究组织数据61所）；Nanjing University of Science and Technology（南京理工大学）；The University of Western Australia（西澳大学）；Hunan University（湖南大学）

本文揭示TFLite与PyTorch Mobile的训练后量化可激活全精度模型中的休眠后门，使int-8模型在触发输入上接近100%攻击成功。

2023-04-27cs.AIcs.CRcs.LG