Defending Person Detection Against Adversarial Patch Attack by Using Universal Defensive Frame

Yu, Youngjoon; Lee, Hong Joo; Lee, Hakmin; Ro, Yong Man

doi:10.1109/tip.2022.3217375

Cited by 7 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means the perturbation generated in the background area usually does not improve the attack effect but may add the perturbed pixels and weaken the invisibility. For patch-based attacks, humans can easily perceive attacks due to the large contrast between patch pixels and image pixels, which is not conducive to the camouflage of targets [34]. These patches usually have a large average gradient, so some defense measures can even detect the location of the target by detecting patch-based attacks [35].…”

Section: Introductionmentioning

confidence: 99%

CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack

Zhou,

Jiang,

Jiang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Object detection algorithms based on convolutional neural networks (CNNs) have achieved remarkable success in remote sensing images (RSIs), such as aircraft and ship detection, which play a vital role in military and civilian fields. However, CNNs are fragile and can be easily fooled. There have been a series of studies on adversarial attacks for image classification in RSIs. However, the existing gradient attack algorithms designed for classification cannot achieve excellent performance when directly applied to object detection, which is an essential task in RSI understanding. Although we can find some works on adversarial attacks for object detection, they are weak in concealment and easily detected by the naked eye. To handle these problems, we propose a target camouflage network for object detection in RSIs, called CamoNet, to deceive CNN-based detectors by adding imperceptible perturbation to the image. In addition, we propose a detection space initialization strategy to maximize the diversity in the detector’s outputs among the generated samples. It can enhance the performance of the gradient attack algorithms in the object detection task. Moreover, a key pixel distillation module is employed, which can further reduce the modified pixels without weakening the concealment effect. Compared with several of the most advanced adversarial attacks, the proposed attack has advantages in terms of both peak signal-to-noise ratio (PSNR) and attack success rate. The transferability of the proposed target camouflage network is evaluated on three dominant detection algorithms (RetinaNet, Faster R-CNN, and RTMDet) with two commonly used remote sensing datasets (i.e., DOTA and DIOR).

show abstract

Section: Introductionmentioning

confidence: 99%

CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack

Zhou,

Jiang,

Jiang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Along with the importance and remarkable achievement in multispectral object detection, DNN-based object detectors are shown to be vulnerable to adversarial patch attacks (Liu et al 2018;Chen et al 2018;Thys, Van Ranst, and Goedemé 2019;Lee and Kolter 2019;Wang et al 2021;Xu et al 2020;Wu et al 2020b;Kim, Yu, and Ro 2022;Yu et al 2022). Adversarial patches are localized perturbations intentionally crafted by malicious attackers that fool machine learning models and lead to misprediction.…”

Section: Introductionmentioning

confidence: 99%

Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors Using Transparent Low-E Films

Kim

2023

AAAI

View full text Add to dashboard Cite

Multispectral object detection plays a vital role in safety-critical vision systems that require an around-the-clock operation and encounter dynamic real-world situations(e.g., self-driving cars and autonomous surveillance systems). Despite its crucial competence in safety-related applications, its security against physical attacks is severely understudied. We investigate the vulnerability of multispectral detectors against physical attacks by proposing a new physical method: Multispectral Invisible Coating. Utilizing transparent Low-e films, we realize a laminated visible-thermal physical attack by attaching Low-e films over a visible attack printing. Moreover, we apply our physical method to manufacture a Multispectral Invisible Suit that hides persons from the multiple view angles of Multispectral detectors. To simulate our attack under various surveillance scenes, we constructed a large-scale multispectral pedestrian dataset which we will release in public. Extensive experiments show that our proposed method effectively attacks the state-of-the-art multispectral detector both in the digital space and the physical world.

show abstract

Enhancing robustness of person detection: A universal defense filter against adversarial patch attacks

Mao,

Chen,

Miao

et al. 2024

Computers & Security

View full text Add to dashboard Cite

Defending Person Detection Against Adversarial Patch Attack by Using Universal Defensive Frame

Cited by 7 publications

References 48 publications

CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack

CamoNet: A Target Camouflage Network for Remote Sensing Images Based on Adversarial Attack

Multispectral Invisible Coating: Laminated Visible-Thermal Physical Attack against Multispectral Object Detectors Using Transparent Low-E Films

Enhancing robustness of person detection: A universal defense filter against adversarial patch attacks

Contact Info

Product

Resources

About