面向车道线检测的隐蔽有效后门攻击：一种自然化数据投毒方法
Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach
用扩散模型在易受攻击区域合成自然化后门触发器，并配合梯度热图定位最优注入位置，为视觉模型后门攻防研究提供了可复用的触发器生成与位置搜索范式。
原文依据 we introduce DBALD, a novel diffusion-based data poisoning framework for generating naturalistic backdoor triggers
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于深度学习的车道线检测（LD）在自动驾驶与高级驾驶辅助系统中发挥着关键作用。然而，其对后门攻击的脆弱性构成了重大的安全隐患。现有针对车道线检测的后门攻击方法往往因触发器人工痕迹明显、易于察觉而实用性有限。为弥补这一局限并探究更具生态效度的后门攻击对车道线检测模型的影响，我们考察了常见的数据投毒攻击，并提出 DBALD——一种用于生成自然化后门触发器的基于扩散的新型数据投毒框架。DBALD 包含两个关键组件：最优触发器位置搜索与隐蔽触发器生成。鉴于攻击效果随触发器位置不同而变化这一观察，我们提出一种基于热图的方法来定位最优触发器位置，并利用梯度分析生成攻击特定的热图。随后，采用基于区域编辑的扩散过程，在前述识别出的最易受攻击区域内合成视觉上合理的触发器。此外，为确保场景完整性与攻击的隐蔽性，我们引入两种损失策略：一种用于保持车道结构，另一种用于维持驾驶场景的一致性。因此，与现有攻击方法相比，DBALD 同时实现了高攻击成功率与更优的隐蔽性。在 4 个主流车道线检测模型上的大量实验表明，DBALD 超越了最优方法，平均成功率提升 +10.87%，且隐蔽性显著增强。实验结果凸显了在车道线检测中确保模型抵御真实世界后门威胁的鲁棒性所面临的重大实际挑战。我们的数据与演示见 https://sites.google.com/view/dbald。
英文原文摘要 1869 字符
Deep learning-based lane detection (LD) plays a critical role in autonomous driving and advanced driver assistance systems. However, its vulnerability to backdoor attacks presents a significant security concern. Existing backdoor attack methods on LD often exhibit limited practical utility due to the artificial and conspicuous nature of their triggers. To address this limitation and investigate the impact of more ecologically valid backdoor attacks on lane detection models, we examine the common data poisoning attack and introduce DBALD, a novel diffusion-based data poisoning framework for generating naturalistic backdoor triggers. DBALD comprises two key components: optimal trigger position finding and stealthy trigger generation. Given the insight that attack performance varies depending on the trigger position, we propose a heatmap-based method to identify the optimal trigger location, with gradient analysis to generate attack-specific heatmaps. A region-based editing diffusion process is then applied to synthesize visually plausible triggers within the most susceptible regions identified previously. Furthermore, to ensure scene integrity and a stealthy attack, we introduce two loss strategies: one for preserving lane structure and another for maintaining the consistency of the driving scene. Consequently, compared to existing attack methods, DBALD achieves both a high attack success rate and superior stealthiness. Extensive experiments on 4 mainstream lane detection models show that DBALD exceeds state-of-the-art methods, with an average success rate improvement of +10.87% and significantly enhanced stealthiness. The experimental results highlight significant practical challenges in ensuring model robustness against real-world backdoor threats in lane detection. Our data and demos are available at https://sites.google.com/view/dbald.