Adversarially-Aware Robust Object Detector

Dong, Zhe; Wei, Pengxu; Li, Lin

doi:10.48550/arxiv.2207.06202

Cited by 2 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We choose adversarial training (AT) as the last countermeasure for X -Adv. Although AT for image classification has been widely studied [25,30], only some preliminary studies have been devoted to object detection [6,10,52]. Here, we adopt RobustDet [10] as the AT method and use an SSD detector with a backbone of VGG-16.…”

Section: Countermeasures Against X -Advmentioning

confidence: 99%

“…Although AT for image classification has been widely studied [25,30], only some preliminary studies have been devoted to object detection [6,10,52]. Here, we adopt RobustDet [10] as the AT method and use an SSD detector with a backbone of VGG-16. Specifically, we adversarially train two detectors using adversarial examples generated by (1) PGD attacks or (2) our X -Adv.…”

Section: Countermeasures Against X -Advmentioning

confidence: 99%

See 1 more Smart Citation

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

Liu¹,

Guo²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Adversarial attacks are valuable for evaluating the robustness of deep learning models. Existing attacks are primarily conducted on the visible light spectrum (e.g., pixel-wise texture perturbation). However, attacks targeting texture-free X-ray images remain underexplored, despite the widespread application of X-ray imaging in safety-critical scenarios such as the X-ray detection of prohibited items. In this paper, we take the first step toward the study of adversarial attacks targeted at X-ray prohibited item detection, and reveal the serious threats posed by such attacks in this safety-critical scenario. Specifically, we posit that successful physical adversarial attacks in this scenario should be specially designed to circumvent the challenges posed by color/texture fading and complex overlapping. To this end, we propose X -Adv to generate physically printable metals that act as an adversarial agent capable of deceiving X-ray detectors when placed in luggage. To resolve the issues associated with color/texture fading, we develop a differentiable converter that facilitates the generation of 3D-printable objects with adversarial shapes, using the gradients of a surrogate model rather than directly generating adversarial textures. To place the printed 3D adversarial objects in luggage with complex overlapped instances, we design a policy-based reinforcement learning strategy to find locations eliciting strong attack performance in worst-case scenarios whereby the prohibited items are heavily occluded by other items. To verify the effectiveness of the proposed X -Adv, we conduct extensive experiments in both the digital and the physical world (employing a commercial X-ray security inspection system for the latter case). Furthermore, we present the physical-world X-ray adversarial attack dataset XAD. We hope this paper will draw more attention to the potential threats targeting safetycritical scenarios. Our codes and XAD dataset are available at https://github.com/DIG-Beihang/X-adv.

show abstract

Section: Countermeasures Against X -Advmentioning

confidence: 99%

Section: Countermeasures Against X -Advmentioning

confidence: 99%

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

Liu¹,

Guo²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Adversarial training methods, such as AdvProp [28] for classification and Det-AdvProp [29] for detection, create adversarial samples and add them to the training process to improve the model's robustness. RobustDet [30] modifies the model framework to defend against attack.…”

Section: Introductionmentioning

confidence: 99%

Robust Airport Surface Object Detection Based on Graph Neural Network

Tang,

2024

Applied Sciences

View full text Add to dashboard Cite

Accurate and robust object detection is of critical importance in airport surface surveillance to ensure the security of air transportation systems. Owing to the constraints imposed by a relatively fixed receptive field, existing airport surface detection methods have not yet achieved substantial advancements in accuracy. Furthermore, these methods are vulnerable to adversarial attacks with carefully crafted adversarial inputs. To address these challenges, we propose the Vision GNN-Edge (ViGE) block, an enhanced block derived from the Vision GNN (ViG). ViGE introduces the receptive field in pixel space and represents the spatial relation between pixels directly. Moreover, we implement an adversarial training strategy with augmented training samples generated by adversarial perturbation. Empirical evaluations on the public remote sensing dataset LEVIR and a manually collected airport surface dataset show that: 1. our proposed method surpasses the original model in precision and robustness; 2. defining the receptive field in pixel space performs better than that on representation space.

show abstract

Adversarially-Aware Robust Object Detector

Cited by 2 publications

References 23 publications

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection

Robust Airport Surface Object Detection Based on Graph Neural Network

Contact Info

Product

Resources

About