Existing adversarial attacks against Object Detectors (ODs) suffer from two inherent limitations. Firstly, ODs have complicated meta-structure designs, hence most advanced attacks for ODs concentrate on attacking specific detector-intrinsic structures, which makes it hard for them to work on other detectors and motivates us to design a generic attack against ODs. Secondly, most works against ODs make Adversarial Examples (AEs) by generalizing image-level attacks from classification to detection, which brings redundant computations and perturbations in semantically meaningless areas (e.g., backgrounds) and leads to an emergency for seeking controllable attacks for ODs. To this end, we propose a generic white-box attack, LGP (local perturbations with adaptively global attacks), to blind mainstream object detectors with controllable perturbations. For a detector-agnostic attack, LGP tracks high-quality proposals and optimizes three heterogeneous losses simultaneously. In this way, we can fool the crucial components of ODs with a part of their outputs without the limitations of specific structures. Regarding controllability, we establish an object-wise constraint that exploits foreground-background separation adaptively to induce the attachment of perturbations to foregrounds. Experimentally, the proposed LGP successfully attacked sixteen state-of-the-art object detectors on MS-COCO and DOTA datasets, with promising imperceptibility and transferability obtained. Codes are publicly released in https://github.com/liguopeng0923/LGP.git

翻译：现有针对目标检测器（ODs）的对抗攻击存在两个固有局限性。首先，目标检测器具有复杂的元结构设计，因此大多数针对ODs的先进攻击都集中于攻击特定的检测器内在结构，这使得它们难以适用于其他检测器，从而促使我们设计一种针对ODs的通用攻击。其次，大多数针对ODs的工作通过将图像级攻击从分类推广到检测来生成对抗样本（AEs），这会在语义无意义区域（如背景）中引入冗余计算和扰动，从而引发了对ODs可控攻击的迫切需求。为此，我们提出了一种通用的白盒攻击方法LGP（局部扰动与自适应全局攻击），通过可控扰动使主流目标检测器失效。为了实现与检测器无关的攻击，LGP追踪高质量候选框并同时优化三个异构损失函数。通过这种方式，我们能够利用ODs的部分输出欺骗其关键组件，而无需受限于特定结构。在可控性方面，我们建立了一种目标级约束，自适应地利用前景-背景分离来引导扰动附着于前景区域。实验结果表明，所提出的LGP成功攻击了MS-COCO和DOTA数据集上的16种最先进目标检测器，并获得了良好的不可感知性和迁移性。代码已在https://github.com/liguopeng0923/LGP.git 公开。