AdvDyn: An Emissivity-based Physical Adversarial Patch for Dynamic Infrared Attack
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Electrical Engineering. The day in electrical engineering: signals, systems and the hardware that carries them.
Rosa: I'm Rosa.
Dev: And I'm Dev, here with Taro.
Rosa: We're looking at the paper: "AdvDyn: An Emissivity-based Physical Adversarial Patch for Dynamic Infrared Attack".
Dev: Here's the gist of the paper. AdvDyn proposes an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation The seamless digital-to-physical transfer via tunable emissivity devices transcends the limitations of traditional static camouflage by establishing a dynamic infrared regulation capability Pruning redundant reasoning tokens The study addresses the limitations of existing physical attack methods, which predominantly employ static thermal suppression strategies that suffer from limited environmental adaptability, insufficient attack robustness, and inadequate visual concealment The research proposes Adv-Camou, an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation This advancement enhances the battlefield survivability of military assets and demonstrates transformative potential for adaptive camouflage in practical combat scenarios How the training signal is built The digital domain involves formulating a multi-level feature confusion mechanism inspired by contrastive representation learning to suppress intrinsic foreground saliency and align perturbed target features with surrounding background distributions in the latent space The loss function combines both background feature alignment term (Lfb) and suppression components (Lff’) to achieve adversarial feature decoupling Specifically, the adversarial objective is decomposed into two dual feature-space operations: 1) attenuation of target saliency representations to induce misclassification as background noise, and 2) alignment of target feature vectors with background distributions in latent space Where the gains come from The physical realization is achieved through a 6×4 array of reversible electrochromic emissivity devices, enabling real-time pattern switching across diverse operational scenarios The optimization process utilizes a differentiable binarization strategy leveraging Gumbel-Softmax reparameterization coupled with a Straight-Through Estimator (STE) to guarantee lossless digital-to-physical realizability on discrete hardware units Furthermore, complexity-aware Expectation Over Transformation (EOT) and keypointdriven perspective warping are integrated to ensure robustness against multiview geometric distortions and long-range atmospheric attenuation Dynamic Adversarial Camouflage Patch Attack The study demonstrates that dynamic patch-switching strategies can restore attack effectiveness and effectively improve the ASR in cross backgrounds, achieving maximum interference energy in complex environments Context-aware patch strategies are employed where Urban Adv-Camou suppresses low-frequency contour features for urban environments, whereas Field Adv-Camou disrupts mid/high-frequency textures for wilderness conditions Experimental results on YOLOv5 demonstrate dynamic patch-switching efficacy, with urban-optimized patches reducing confidence scores from 0.42 to 0.13 in cityscapes, while wilderness-adapted patches decrease scores from 0.39 to 0.21 in natural settings Physical Deployment and Robustness Experimental results demonstrate that increasing the relative patch size from 0.18 to 0.28 linearly improved the ASR by 42.66% (from 46.77% to 89.43%), as shown in Fig.
Rosa: 2(b) Grayscale values significantly influenced thermal contrast, with extreme values (0 or 1) maximizing ASR (82.44% for grayscale 0 and 60.39% for grayscale 1), while intermediate values reduced ASR to 34.78% due to similarity with background grayscale (≈0.7) The dynamic patch-switching strategy enhances cross-scenario adaptability, yielding 13 15% average ASR improvement and validating the superiority of dynamic physical attacks This research establishes a multi-angle, highsuccess-rate adversarial attack framework against infrared pedestrian detectors in real-world settings, showcasing AdvCamou’s robustness across environments and devices The findings confirm that coordinated optimization of dynamic emissivity devices and adversarial algorithms achieves lossless digital-to-physical transfer across varying observation distances Adv-Camou provides a groundbreaking solution for infrared adversarial camouflage, with its dynamic response and crossscene robustness significantly enhancing battlefield survivability Future directions include developing lightweight Transformer-based decision networks integrated with multimodal sensors for realtime environmental perception and millisecond-level dynamic control via reinforcement learning Developing thermochromic materials for visible-infrared dual-band perturbations to construct multispectral cooperative attack systems is another proposed direction Leveraging physics-informed GANs to simulate extreme thermal noise scenarios and meta-learning frameworks to improve patch adaptability are also identified as future research pathways REFERENCES
1: S.
Dev: Ren, K.
Rosa: He, R.
Title and authors: Rosa: Now, let's talk about what this paper is actually proposing in detail. The title itself says "AdvDyn: An Emissivity-based Physical Adversarial Patch for Dynamic Infrared Attack." It immediately tells us the core mechanism involves using emissivity devices—basically materials that control how much heat they radiate—and making it dynamic.
Dev: That dynamic aspect is key, Rosa. They’re not just talking about a material that works; they’re talking about a system where the patch can switch patterns in real time based on what's happening around it. This means it can react to changes on the battlefield or in a complex environment rather than being stuck in one fixed camouflage setting.
Rosa: So, instead of just having one way to hide from infrared detectors, you have this patch that can actively regulate its thermal signature. This transitions the attack from something static to something much more responsive and adaptive.
Dev: And the authors explain how they build that responsiveness using a multi-level loss function based on feature confusion mechanisms. They are trying to trick the detectors by both reducing the target's distinct heat signature and making sure it blends in with whatever is already there, like the background.
Rosa: It sounds like they are tackling two problems at once: hiding what you want to hide, and making sure you look like part of the scenery. That’s a smart way to approach physical camouflage.
The paper's summary: Dev: Let's unpack their summary a bit more. Essentially, they are proposing Adv-Camou as an emissivity-based patch that achieves advancements from static to dynamic attacks through this co-innovation idea. They lay out how the digital side uses feature confusion mechanisms to suppress the target saliency and align it with background distributions in the latent space, which is what they call Lfb and Lff’.
Rosa: So, on the physical side, they realize that using active heating elements or phase-change materials often runs into problems like thermal diffusion and heat loss. But they focus on passive emissivity-based materials because those can define sharp edges better than active ones, even if they are limited to discrete states.
Dev: That's a crucial distinction. They are optimizing for the manufacturability of physical units while still linking it back to continuous digital gradients using something called a differentiable binarization strategy with Gumbel-Softmax reparameterization and a Straight-Through Estimator. It’s their way of making the digital plan turn into physical parts without losing that connection.
Rosa: I like that they have this loss function setup to handle both the feature alignment and the saliency attenuation simultaneously. It shows they are thinking about how to build a system where the algorithm and the material work together seamlessly, not just as separate things.
The paper's improvements: Dev: Now for what they claim as their improvements. They focus on three main areas: adaptive physical transformation, contrastive feature confusion in the digital domain, and then this specific context-aware patch strategy. They show that dynamic patch-switching can actually improve the attack effectiveness and the adversarial success rate in cross backgrounds.
Rosa: Specifically, they introduce context-aware patch strategies. If you're in an urban setting, they use Urban AdvCamou to suppress low-frequency contour features so you blend into city shapes. But if you’re out in the wilderness, Field AdvCamou disrupts mid and high-frequency textures for a different effect.
Dev: And the numbers they show are pretty telling about this adaptability. They demonstrate that urban-optimized patches reduce confidence scores from zero point forty-two to zero point thirteen in cityscapes, while wilderness-adapted patches decrease those scores from zero point thirty-nine to zero point twenty-one in natural settings. That's a noticeable improvement based on the environment.
Rosa: They also show that increasing the relative patch size from zero point one eight up to zero point two eight linearly improved the adversarial success rate by a factor of four-two-point-six six percent, going from forty-six point seventy-seven percent up to eighty-nine point forty-three percent. That shows that physical size matters for performance in this setup.
Conclusion: Dev: So, wrapping up the main points of "AdvDyn: An Emissivity-based Physical Adversarial Patch for Dynamic Infrared Attack," we see a framework that achieves multi-angle, high success-rate attacks against infrared pedestrian detectors across real-world settings. The core finding is that coordinating the optimization of dynamic emissivity devices with the adversarial algorithms allows for a lossless digital to physical transfer even when observation distances are varying.
Rosa: It really confirms that this AdvCamou solution, with its dynamic response and cross-scene robustness, significantly enhances battlefield survivability by showing how these two worlds—the algorithm and the physical device—can be tightly coupled for better results. The paper shows a robust way to achieve that adaptability we discussed earlier.
Taro: I wonder if this system can handle unexpected world misbehavior outside the lab. When things get chaotic, does the dynamic switching remain reliable, or does it drift into an unstable state? That's where my testing comes in—how gracefully it recovers when the environment isn't exactly what the training data predicted.
Dev: That’s a fair question, Taro. The paper focuses on how the system performs under controlled cross-scenario testing and geometric distortions, but real-world unpredictability is always a hurdle for any physical loop you build. We need to see how fast that dynamic control can actually respond when things change rapidly on the fly.
Rosa: For now, it’s clear that AdvDyn sets a strong foundation for building these kinds of adaptive physical camouflage systems by proving this digital-to-physical transfer is achievable in a way that handles environmental context. That's where we leave it for now.
National University of Defense Technology · Xiangtan University
eess.IV
Submitted: 2026-10-15
Updated: 2026-11-16
Comments: 11 pages, 6 figures
Code: https://github.com/ultralytics/ultralytics
License: http://creativecommons.org/licenses/by/4.0/
Importance score: 86/100
The gist: AdvDyn proposes an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation The…
Key concepts
- Emissivity-based Physical Dynamic Adversarial Patch
- This is a physical device made of reversible electrochromic materials that can change how much infrared radiation it emits. Instead of a static camouflage, this patch can actively switch its thermal signature in real-time to match the surrounding environment, making it much harder for infrared detectors to spot.
- Multi-level Feature Confusion Mechanism
- This digital technique uses contrastive learning ideas to manipulate the input image features. It aims to hide the target object's unique visual characteristics by suppressing its obvious saliency and blending its features into the general appearance of the background in a mathematical space.
- Algorithm-Material Co-innovation
- This refers to designing both the software (the algorithm) and the physical hardware (the material) simultaneously. The paper shows how a specific digital strategy is perfectly matched with a physical device structure, ensuring that when the algorithm dictates a change, the physical patch can execute it losslessly.
- Dynamic Scene Adaptation
- The system intelligently switches between different camouflage patterns based on the context of where it is deployed. For example, it uses one pattern optimized for city environments (suppressing low-frequency features) and another for wilderness settings (disrupting textures), ensuring maximum effectiveness regardless of the background.
Terminology
Summary
AdvDyn proposes an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation The seamless digital-to-physical transfer via tunable emissivity devices transcends the limitations of traditional static camouflage by establishing a dynamic infrared regulation capability
Pruning redundant reasoning tokens
The study addresses the limitations of existing physical attack methods, which predominantly employ static thermal suppression strategies that suffer from limited environmental adaptability, insufficient attack robustness, and inadequate visual concealment The research proposes Adv-Camou, an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation This advancement enhances the battlefield survivability of military assets and demonstrates transformative potential for adaptive camouflage in practical combat scenarios
How the training signal is built
The digital domain involves formulating a multi-level feature confusion mechanism inspired by contrastive representation learning to suppress intrinsic foreground saliency and align perturbed target features with surrounding background distributions in the latent space The loss function combines both background feature alignment term (Lfb) and suppression components (Lff’) to achieve adversarial feature decoupling Specifically, the adversarial objective is decomposed into two dual feature-space operations: 1) attenuation of target saliency representations to induce misclassification as background noise, and 2) alignment of target feature vectors with background distributions in latent space
Where the gains come from
The physical realization is achieved through a 6×4 array of reversible electrochromic emissivity devices, enabling real-time pattern switching across diverse operational scenarios The optimization process utilizes a differentiable binarization strategy leveraging Gumbel-Softmax reparameterization coupled with a Straight-Through Estimator (STE) to guarantee lossless digital-to-physical realizability on discrete hardware units Furthermore, complexity-aware Expectation Over Transformation (EOT) and keypointdriven perspective warping are integrated to ensure robustness against multiview geometric distortions and long-range atmospheric attenuation
Dynamic Adversarial Camouflage Patch Attack
The study demonstrates that dynamic patch-switching strategies can restore attack effectiveness and effectively improve the ASR in cross backgrounds, achieving maximum interference energy in complex environments Context-aware patch strategies are employed where Urban Adv-Camou suppresses low-frequency contour features for urban environments, whereas Field Adv-Camou disrupts mid/high-frequency textures for wilderness conditions Experimental results on YOLOv5 demonstrate dynamic patch-switching efficacy, with urban-optimized patches reducing confidence scores from 0.42 to 0.13 in cityscapes, while wilderness-adapted patches decrease scores from 0. p. 8 Experimental results on YOLOv5 demonstrate dynamic
patch-switching efficacy: urban-optimized patches reduce
confidence scores from 0. 13 in cityscapes, while
wilderness-adapted patches decrease scores from 0.Where the paper says it
Physical Deployment and Robustness
Experimental results demonstrate that increasing the relative patch size from 0.18 to 0.28 linearly improved the ASR by 42. p. 5 Experimental results demonstrated that increasing the relative
patch size from 0. 28 linearly improved the ASR by
42. The feature
confusion loss was minimized using a momentum SGD
optimizer (batch size: 8, initial learning rate: 0. As shown
in Fig. Notably, under identical size constraints, Adv-Camou
achieved 41% higher ASR than the baseline black patch,
underscoring the necessity of structural optimization. Grayscale values significantly influenced thermal contrast:
extreme values (0 or 1) maximized ASR (82. Nevertheless, directly transferring
visible-light adversarial paradigms to the thermal infrared
domain remains fundamentally constrained by discrepancies
in imaging physics. While visible-light cameras resolve highfrequency spatial textures across three chromatic channels
(RGB), thermal imagers record single-channel grayscale
intensity maps that reflect surface temperature and material
emissivity distributions. 2(c)), while
intermediate values (e. 6) reduced ASR to 34. 6) reduced ASR to 34. 78% due to
similarity with background grayscale (≈0.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Conclusion
This research establishes a multi-angle, highsuccess-rate adversarial attack framework against infrared pedestrian detectors in real-world settings, showcasing AdvCamou’s robustness across environments and devices The findings confirm that coordinated optimization of dynamic emissivity devices and adversarial algorithms achieves lossless digital-to-physical transfer across varying observation distances Adv-Camou provides a groundbreaking solution for infrared adversarial camouflage, with its dynamic response and crossscene robustness significantly enhancing battlefield survivability Future directions include developing lightweight Transformer-based decision networks integrated with multimodal sensors for realtime environmental perception and millisecond-level dynamic control via reinforcement learning Developing thermochromic materials for visible-infrared dual-band perturbations to construct multispectral cooperative attack systems is another proposed direction Leveraging physics-informed GANs to simulate extreme thermal noise scenarios and meta-learning frameworks to improve patch adaptability are also identified as future research pathways
REFERENCES
[1] S. Ren, K. He, R. Girshick, and J. p. 9 REFERENCES
[1] S. Girshick, and J. Sun, "Faster R-CNN: Towards real-time
object detection with region proposal networks," IEEE Trans. Pattern Anal. Sun, "Faster R-CNN: Towards real-time
object detection with region proposal networks," IEEE Trans. Pattern Anal. Sun, "Faster R-CNN: Towards real-time
object detection with region proposal networks," IEEE Trans. Pattern Anal. Sun, "Faster R-CNN: Towards real-time
object detection with region proposal networks," IEEE Trans. Pattern Anal. Pattern Anal. 1137–1149, Jun.Where the paper says it
Faster R-CNN: Towards real-time object detection with region proposal networks,
IEEE Trans. Pattern Anal. p. 9Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[2] T.-Y. Lin, P. Goyal, R. Girshick, K. p. 9 REFERENCES
[1] S. Girshick, and J.Where the paper says it
Focal loss for dense object detection,
IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp: 318–327
[3] N. Carion, F. Massa, G. Synnaeve, N. p. 9 318–327, Feb. Synnaeve, N. Synnaeve, N. Usunier, A. Usunier, A. Kirillov, and S. Zagoruyko, "End-to-end object detection with transformers," in
Proc. (ECCV), Glasgow, U. Zagoruyko, "End-to-end object detection with transformers," in
Proc. (ECCV), Glasgow, U.Where the paper says it
Where the paper says it
Where the paper says it
End-to-end object detection with transformers,
in Proc: Eur: Conf.: Comput.: Vis.: Glasgow, U. p. 9Where the paper says it
Where the paper says it
[4] C. Szegedy et al. p. 9 , 2020, pp. Szegedy et al. These factors blur the sharp boundaries required for
high-frequency adversarial patterns and introduce
uncontrollable thermal drift. Conversely, passive emissivitybased materials offer superior edge definition but can only
represent discrete binary or tertiary states, creating a
substantial optimization gap between continuous digital
gradients and discrete physical fabrication. These factors blur the sharp boundaries required for
high-frequency adversarial patterns and introduce
uncontrollable thermal drift. Conversely, passive emissivitybased materials offer superior edge definition but can only
represent discrete binary or tertiary states, creating a
substantial optimization gap between continuous digital
gradients and discrete physical fabrication. These factors blur the sharp boundaries required for
high-frequency adversarial patterns and introduce
uncontrollable thermal drift. Conversely, passive emissivitybased materials offer superior edge definition but can only
represent discrete binary or tertiary states, creating a
substantial optimization gap between continuous digital
gradients and discrete physical fabrication.Where the paper says it
Intriguing properties of neural networks,
in Proc: Int.: Conf.: Learn.: Represent. p. 1Where the paper says it
Where the paper says it
Where the paper says it
[5] I. J. Goodfellow, J. Shlens, and C. Szegedy, Explaining and harnessing adversarial examples,
in Proc: Int.: Conf.: Learn.: Represent., San Diego, CA, USA, 2015
[6] M. Sharif et al., Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition,
in Proc: ACM SIGSAC Conf.: Comput.: Commun.: Secur., Vienna, Austria, 2016
[7] T. B. Brown et al., Unlike visible-light
sensors that rely on reflected ambient illumination, thermal
infrared sensors capture long-wave infrared (LWIR, 8–14 μm)
radiation emitted directly by objects as governed by the
Stefan-Boltzmann law. Empowered by rapid advancements in
deep convolutional neural networks (CNNs) and Vision
Transformers (ViTs) [1][2][3], modern infrared detectors
achieve remarkable precision under degraded visual
conditions, including total darkness, dense fog, and heavy
smoke.Adversarial patch,
in Proc: Adv.: Neural Inf. p. 0Where the paper says it
[8] K. Eykholt et al., Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios. Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios. Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios. Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios. Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios. Furthermore, we integrate complexity-aware
Expectation Over Transformation (EOT) [26] and keypointdriven perspective warping to ensure robustness against multiview geometric distortions and long-range atmospheric
attenuation. In the physical domain, we fabricate a 6 × 4
individually addressable array of reversible electrochromic
emissivity devices, enabling real-time pattern switching across
diverse operational scenarios.Robust physical-world attacks on deep learning visual classification,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit. p. 1Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
[9] K. Xu et al., Adversarial T-shirt! Evading person detectors in a physical world,
in Proc: Eur.: Conf.: Comput.: Vis.: Glasgow, U.K., 2020
[10] Z. Hu et al., Adversarial texture for fooling person detectors in the physical world,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit., New Orleans, LA, USA, 2022
[11] H. Wei et al., Fooling thermal infrared detectors with a novel wearable design,
in Proc: AAAI Conf.: Artif. Intell., vol. 37, no. 12, 2023
[12] X. Zhu et al., Fooling thermal infrared pedestrian detectors in real world using small bulbs,
in Proc: AAAI Conf.: Artif. Intell., vol. 35, no. 4, 2021
[13] C. Hu et al., Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world,
Neural Netw., vol. 175, Jul. 2024
[14] X. Wei et al., Unified adversarial patch for visible-infrared cross-modal attacks in the physical world,
IEEE Trans. Pattern Anal. Mach. Intell., vol: 46, no.: 4, pp: 2348–2363, Apr: 2024
[15] K. Tiliwalidi et al. p. 2 applied Differential Evolution (DE) and PSO to optimize
thermal blocks (AdvIB) [13] and Bézier-curved strips (AdvIC)
[18]. Similarly, Tiliwalidi et al. applied Differential Evolution (DE) and PSO to optimize
thermal blocks (AdvIB) [13] and Bézier-curved strips (AdvIC)
[18]. Similarly, Tiliwalidi et al.Where the paper says it
Where the paper says it
AdvGrid: A multi-view black-box attack on infrared pedestrian detectors in the physical world,
Appl. Soft Comput., vol: 174, 2025
[16] Z. Hu et al., Physically structured adversarial patch inspired by natural leaves multiply angles deceives infrared detectors via 3D modeling,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit., Vancouver, BC, Canada, 2023
[17] X. Zhu et al., Infrared invisible clothing: Hiding from infrared detectors at multiple angles in real world,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit., New Orleans, LA, USA, 2022
[18] C. Hu et al., Adversarial infrared curves: An attack on infrared pedestrian detectors in the physical world,
Neural Netw., vol. 178, Oct.: 2024
[19] K. Tiliwalidi et al., Adversarial infrared geometry: Using geometry to perform adversarial attack against infrared pedestrian detectors,
2024, arXiv:arXiv:arXiv:arXiv: arXiv:arXiv: arXiv-2403.03674
[20] C. Hu et al., Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical world,
Appl. Soft Comput., vol: 171, 2025
[21] X. Wei, J. Yu, and Y. Huang, Physically adversarial infrared patches with learnable shapes and locations,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit., Vancouver, BC, Canada, 2023
[22] O. Salihoglu et al., Graphene-based adaptive thermal camouflage,
Nano Lett., vol: 18, no.: 7, pp: 4541–4548, Jul.: 2018
[23] M. S. Ergoktas et al., Multispectral graphene-based electro-optical surfaces with reversible tunability from visible to microwave wavelength,
Nature Photon., vol: 15, no.: 7, pp: 493–498, Jul.: 2021
[24] Y. Wang et al., Visible-infrared compatible and independent camouflage with multicolor patterns and tunable emissivity,
Nanophotonics, vol: 13, no.: 18, pp: 3123–3133, May: 2024
[25] E. Jang, S. Gu, and B. Poole, Categorical reparameterization with Gumbel-Softmax,
in Proc: Int.: Conf.: Learn.: Represent., Toulon, France, 2017
[26] A. Athalye et al., Synthesizing robust adversarial examples,
in Proc: Int.: Conf.: Mach. Learn., Stockholm, Sweden, 2018
[31] Z. Zhou et al. p. 2 3
> REPLACE THIS LINE WITH YOUR MANUSCRIPT ID NUMBER (DOUBLE-CLICK HERE TO EDIT) <
contexts and artistic textures, respectively, whereas Zhou et al. [31] balanced perceptual realism with deception strength.Where the paper says it
MVPatch: More vivid patch for adversarial camouflaged attacks on object detectors in the physical world,
2023, arXiv:arXiv:arXiv:arXiv-2312.17431
[35] L. Huang et al. p. 2 Because planar patches fail under
severe viewing angles and non-rigid human motion, wearable
adversarial camouflage has emerged as a prominent research
trajectory. [9] introduced Thin Plate Spline (TPS)
transformations to model the non-rigid wrinkling of
adversarial T-shirts, while Huang et al.Where the paper says it
Universal physical camouflage attacks on object detectors,
in Proc: IEEE/CVF Conf.: Comput.: Vis. Pattern Recognit., Seattle, WA, USA, 2020
[39] J. Cheng et al. p. 0 1
> REPLACE THIS LINE WITH YOUR MANUSCRIPT ID NUMBER (DOUBLE-CLICK HERE TO EDIT) <
Adv-Camou: An Emissivity-based Physical Dynamic
Adversarial Patch for Infrared Attack
Zhuo Chen, Xu Zheng, Runyun He, Tuoyu Liu, Kaixuan Ding, Yufei Ge, Yijing Song, Tingting Shi, Haining Ji,
Pinghua Tang, Haifeng Cheng, Xikun Hu, Dongqing Liu
Abstract—With the widespread application of infrared object
detection technologies in military domains, intelligent infrared
adversarial camouflage capabilities have become critical. Existing physical attack methods predominantly employ static
thermal suppression strategies, suffering from limited
environmental adaptability, insufficient attack robustness, and
inadequate visual concealment.Where the paper says it
DePatch: Towards robust adversarial patch for evading person detectors in the real world,
2024, arXiv:arXiv:arXiv:arXiv-2408.06625
[41] T. Feng et al., IC9600: A benchmark dataset for automatic image complexity assessment,
IEEE Trans. Pattern Anal. Mach. Intell., vol: 45, no.: 7, pp: 8577–8593, Jul.: 2023
[43] G. Jocher, YOLOv5 by Ultralytics (Version 7.0),
Zenodo, 2020
[45] G. Jocher, A. Chaurasia, and J. Qiu, Ultralytics YOLO (Version 8.0.0),
GitHub, 2023
[46] W. Liu et al., SSD: Single shot multibox detector,
in Proc: Eur.: Conf.: Comput.: Vis.: Amsterdam, The Netherlands, 2016
[59] A multidimensional experimental framework was designed to comprehensively evaluate adversarial camouflage patches’ effectiveness under real-world variables including distance, viewing angle, and complex backgrounds
[60] Experimental results (Fig. 3) demonstrate 94. p. 0 A 6×4 array of reversible electrochromic
emissivity device is developed and tested across a range of
background scenarios, enabling scene-adaptive dynamic
camouflage through independent unit control. Experiments
demonstrate that this method achieves 95. 3) demonstrate 94. 45% average ASR across scenarios,
peaking at 98. 45% average ASR across scenarios,
peaking at 98. 2% for close-range (2 m) attacks and
maintaining 90.Where the paper says it
Where the paper says it
Where the paper says it
[61] Extreme lateral angles (±45°) achieved 91.
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
-
Adaptive physical transformation enables real-time scene-adaptive dynamic camouflage through independent unit control by using a 6×4 array of reversible electrochromic emissivity devices to switch patterns based on environmental context.
-
Contrastive feature confusion mechanism suppresses intrinsic foreground saliency and aligns perturbed target features with background distributions in the latent space, enhancing attack efficacy and crossarchitecture transferability across CNN- and Transformerbased infrared detectors.
-
Differentiable discrete pattern optimization bridges continuous gradient optimization with discrete, manufacturable emissivity unit arrays using Gumbel-Softmax reparameterization coupled with a Straight-Through Estimator to ensure lossless digital-to-physical realizability.
-
AlgorithmHardware CoDesign allows for the implementation of context-aware patch strategies where Urban AdvCamou suppresses low-frequency contour features for urban environments and Field AdvCamou disrupts mid/high-frequency textures for wilderness conditions.
-
The system can achieve superior performance in complex scenarios by utilizing dynamic scene adaptation, such as Urban AdvCamou achieving 80.43% ASR in the urban background versus 52.78% for generic patches.
Abstract
With the widespread application of infrared object detection technologies in military domains, intelligent infrared adversarial camouflage capabilities have become critical. Existing physical attack methods predominantly employ static thermal suppression strategies, suffering from limited environmental adaptability, insufficient attack robustness, and inadequate visual concealment. This study proposes AdvDyn, an emissivity-based physical dynamic adversarial patch that achieves paradigm-shifting advancements from static to dynamic attacks through algorithm-material co-innovation. First, a multi-level loss function based on feature confusion mechanisms is designed to deceive detectors by attenuating target saliency and enforcing background feature alignment. Second, adaptive physical transformations and differentiable binarization optimization are integrated to address physical robustness and realizability constraints. A 6*4 array of reversible electrochromic emissivity device is developed and tested across a range of background scenarios, enabling scene-adaptive dynamic adversarial attack through independent unit control. Experiments demonstrate that this method achieves 95.59% attack success rate (ASR), reducing average precision (AP) by 60.51%. Physical validations show that static adversarial patches attain 76.55% average ASR under multi-view, multi-range, and multi-spectral conditions, while dynamic patches enhance ASR up to 91.55% in complex environments (wilderness/urban) through adaptive switching. The seamless digital-to-physical transfer via tunable emissivity devices transcends the limitations of traditional static adversarial attack by establishing a dynamic infrared regulation capability. This advancement enhances the battlefield survivability of military assets and demonstrates transformative potential for adaptive adversarial attack in practical combat scenarios.
Sources
- Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors
- Categorical Reparameterization with Gumbel-Softmax
- MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World
- DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World
- YOLOv3: An Incremental Improvement
Related papers
- HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
- Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
- FDIR: Fidelity-Anchored Decompressed Image Restoration for Human and Machine Perception
- A Disease-Centric Vision-Language Foundation Model for Precision Oncology in Kidney Cancer
- CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography
- Task-Aware Bitrate Thresholds for Codec-Robust Ultrasound Segmentation