Adversarial Attack with Raindrops

Liu, Jiyuan; Lu, Bingyi; Xiong, Mingkang; Zhang, Tao; Xiong, Hao

doi:10.48550/arxiv.2302.14267

Cited by 4 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Introduced in [37], FID originally served as a metric to evaluate the performance of GANs by assessing the similarity of generated images. FID is one of the recent tools for assessing the visual quality of adversarial images and it aligns closely with human judgment (see [38][39][40]). On the other hand, [41,42] provide an assessment of L p -norms as a measure of perceptual distance between images.…”

Section: Assessment Of the Human Perception Of Distinct Imagesmentioning

confidence: 99%

The Noise Blowing-Up Strategy Creates High Quality High Resolution Adversarial Images against Convolutional Neural Networks

Topal,

Mancellari,

Leprévost

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) serve as powerful tools in computer vision tasks with extensive applications in daily life. However, they are susceptible to adversarial attacks. Still, attacks can be positive for at least two reasons. First, revealing CNNs’ vulnerabilities prompts efforts to enhance their robustness. Second, adversarial images can also be employed to preserve private and sensitive information from CNN-based threat models aiming to extract such data from images. For such applications, the construction of high-resolution adversarial images is mandatory in practice. This paper achieves the following: first, it quantifies the speed, adversity, and visual quality challenges involved in the effective construction of high-resolution adversarial images; second, it provides the operational design of a new strategy, called here the noise blowing-up strategy, which works for any attack, any scenario, any CNN, and any clean image; third, it validates this strategy via an extensive series of experiments. We performed experiments with 100 high-resolution clean images, exposing them to 7 different attacks against 10 CNNs. Our method achieved an overall average success rate of 75% in the targeted scenario and 64% in the untargeted scenario. We revisited the failed cases and performed a slight modification to our method, which led to success rates larger than 98.9%. As of today, the noise blowing-up strategy is the first generic approach that successfully solves all three speed, adversity, and visual quality challenges, therefore effectively constructing high-resolution adversarial images with high-quality requirements.

show abstract

Section: Assessment Of the Human Perception Of Distinct Imagesmentioning

confidence: 99%

The Noise Blowing-Up Strategy Creates High Quality High Resolution Adversarial Images against Convolutional Neural Networks

Topal,

Mancellari,

Leprévost

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The goal of these works is to obtain the minimum perturbation by optimising the generation while being able to obtain robust adversarial effects. In recent studies, the raindrop attack has been introduced as a notable technique for assessing the efficacy of using simulated raindrops as perturbations [35,36]. This approach enables researchers to evaluate the impact of raindrop-like perturbations on deep neural networks and subsequently develop defence mechanisms to enhance the DNNs' resilience against such attacks.…”

Section: Digital Attacksmentioning

confidence: 99%

Adversarial catoptric light: An effective, stealthy and robust physical‐world attack to DNNs

Hu,

Shi,

Tian

et al. 2024

IET Computer Vision

View full text Add to dashboard Cite

Recent studies have demonstrated that finely tuned deep neural networks (DNNs) are susceptible to adversarial attacks. Conventional physical attacks employ stickers as perturbations, achieving robust adversarial effects but compromising stealthiness. Recent innovations utilise light beams, such as lasers and projectors, for perturbation generation, allowing for stealthy physical attacks at the expense of robustness. In pursuit of implementing both stealthy and robust physical attacks, the authors present an adversarial catoptric light (AdvCL). This method leverages the natural phenomenon of catoptric light to generate perturbations that are both natural and stealthy. AdvCL first formalises the physical parameters of catoptric light and then optimises these parameters using a genetic algorithm to derive the most adversarial perturbation. Finally, the perturbations are deployed in the physical scene to execute stealthy and robust attacks. The proposed method is evaluated across three dimensions: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the efficacy of the proposed method, achieving an attack success rate of 83.5%, surpassing the baseline. The authors utilise common catoptric light as a perturbation to enhance the method's stealthiness, rendering physical samples more natural in appearance. Robustness is affirmed by successfully attacking advanced DNNs with a success rate exceeding 80% in all cases. Additionally, the authors discuss defence strategies against AdvCL and introduce some light‐based physical attacks.

show abstract

“…Some recent works have also focused on other image attributes, such as color, texture, and camouflage, to generate attacks [26][27][28][29][30]. Additionally, some scholars [31] [32] have utilized digital synthesis methods to simulate raindrops to deploy adversarial attacks, subsequently using these generated adversarial samples to improve the model's robustness. These works have been primarily conducted in digital environments, where attackers can directly modify input images to generate adversarial samples.…”

Section: Adversarial Attacks In the Visible Light Fieldmentioning

confidence: 99%

Adversarial Texture for Fooling Person Detectors in the Physical World

Huang

Zhu

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Infrared imaging systems have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern. However, few studies have explored the safety of infrared imaging systems in real-world settings. Previous research has used physical perturbations such as small bulbs and thermal "QR codes" to attack infrared imaging detectors, but such methods are highly visible and lack stealthiness. Other researchers have used hot and cold blocks to deceive infrared imaging detectors, but this method is limited in its ability to execute attacks from various angles. To address these shortcomings, we propose a novel physical attack called adversarial infrared blocks (AdvIB). By optimizing the physical parameters of the adversarial infrared blocks, this method can execute a stealthy black-box attack on thermal imaging system from various angles. We evaluate the proposed method based on its effectiveness, stealthiness, and robustness. Our physical tests show that the proposed method achieves a success rate of over 80% under most distance and angle conditions, validating its effectiveness. For stealthiness, our method involves attaching the adversarial infrared block to the inside of clothing, enhancing its stealthiness. Additionally, we test the proposed method on advanced detectors, and experimental results demonstrate an average attack success rate of 51.2%, proving its robustness. Overall, our proposed AdvIB method offers a promising avenue for conducting stealthy, effective and robust black-box attacks on thermal imaging system, with potential implications for real-world safety and security applications.

show abstract

Adversarial Attack with Raindrops

Cited by 4 publications

References 34 publications

The Noise Blowing-Up Strategy Creates High Quality High Resolution Adversarial Images against Convolutional Neural Networks

The Noise Blowing-Up Strategy Creates High Quality High Resolution Adversarial Images against Convolutional Neural Networks

Adversarial catoptric light: An effective, stealthy and robust physical‐world attack to DNNs

Adversarial Texture for Fooling Person Detectors in the Physical World

Contact Info

Product

Resources

About