攻击者可植入隐蔽能量后门，使模型在特定输入时耗能飙升。
Energy Backdoor Attack to Deep Neural Networks
- 通过两阶段攻击，在稀疏加速器上植入能量后门
- 触发样本能耗提升超10倍，正常输入性能不变
- 适合研究硬件安全与模型鲁棒性的开发者
深度学习的兴起增加了计算复杂性和能耗，促使在边缘和移动设备中采用专用集成电路（ASIC）以实现能效优化。然而，近期研究已揭示这些加速器对能耗攻击的脆弱性。尽管已有多种推理阶段能耗攻击被提出，但针对深度神经网络的能量后门攻击仍处于空白。本文设计了一种创新的能量后门攻击，针对基于稀疏性的加速器上的深度神经网络。攻击分为两个阶段：后门注入与隐蔽性验证。实验使用ResNet-18和MobileNet-V2模型在CIFAR-10与Tiny ImageNet数据集上训练，结果表明，该攻击可在触发样本上显著提高能耗，同时保持正常输入的模型性能。这证明了深度神经网络在能量后门攻击下的脆弱性。攻击源码已开源：https://github.com/hbrachemi/energy_backdoor。
原文摘要 · Abstract (English)
The rise of deep learning (DL) has increased computing complexity and energy use, prompting the adoption of application specific integrated circuits (ASICs) for energy-efficient edge and mobile deployment. However, recent studies have demonstrated the vulnerability of these accelerators to energy attacks. Despite the development of various inference time energy attacks in prior research, backdoor energy attacks remain unexplored. In this paper, we design an innovative energy backdoor attack against deep neural networks (DNNs) operating on sparsity-based accelerators. Our attack is carried out in two distinct phases: backdoor injection and backdoor stealthiness. Experimental results using ResNet-18 and MobileNet-V2 models trained on CIFAR-10 and Tiny ImageNet datasets show the effectiveness of our proposed attack in increasing energy consumption on trigger samples while preserving the model's performance for clean/regular inputs. This demonstrates the vulnerability of DNNs to energy backdoor attacks. The source code of our attack is available at: https://github.com/hbrachemi/energy_backdoor.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。