Academic Journal
A Patch Can Disrupt Live Video Streaming: Physical Adversarial Attacks on Deep Learning Compression.
| Title: | A Patch Can Disrupt Live Video Streaming: Physical Adversarial Attacks on Deep Learning Compression. |
|---|---|
| Authors: | Yang, Yuqing, Nguyen, Anh, Yan, Zhisheng |
| Source: | ACM Transactions on Multimedia Computing, Communications & Applications; Sep2025, Vol. 21 Issue 9, p1-23, 23p |
| Subject Terms: | Live streaming, Streaming video & television, Client/server computing equipment, Consumption (Economics), Cameras |
| Abstract: | Deep learning (DL)-based compression has achieved outstanding performance compared to traditional compression. However, due to the vulnerability of adversarial attacks on DL models, understanding the security of DL-based compression is crucial. Previous attacks have demonstrated the feasibility of failing DL-based compression models in the digital domain. However, these attacks rely on perfect digital modification of the whole image and internal access to camera/server files, preventing their usage in the physical world where such assumptions do not hold. In this article, we unveil the first physical adversarial attack targeting DL-based compression in the context of live video streaming. The proposed attack, namely CamHack, places a small-sized physical patch in the visual scene covered by the live camera to manipulate the bitrate of compressed content and disrupt live streaming. The patch is crafted to address color and geometric transformations in diverse streaming scenes while remaining inconspicuous. Extensive experiments in various streaming scenes and network conditions show that CamHack increases bit consumption by 276.58%, 384.74%, and 942.28% over the clean scene without a patch on three representative victim models. CamHack is also robust under various practical impacts such as patch location, lighting conditions, and patch size. [ABSTRACT FROM AUTHOR] |
| Copyright of ACM Transactions on Multimedia Computing, Communications & Applications is the property of Association for Computing Machinery and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Complementary Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edb&genre=article&issn=15516857&ISBN=&volume=21&issue=9&date=20250901&spage=1&pages=1-23&title=ACM Transactions on Multimedia Computing, Communications & Applications&atitle=A%20Patch%20Can%20Disrupt%20Live%20Video%20Streaming%3A%20Physical%20Adversarial%20Attacks%20on%20Deep%20Learning%20Compression.&aulast=Yang%2C%20Yuqing&id=DOI:10.1145/3750047 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 188146297 RelevancyScore: 1007 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1007.33947753906 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Patch Can Disrupt Live Video Streaming: Physical Adversarial Attacks on Deep Learning Compression. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Yang%2C+Yuqing%22">Yang, Yuqing</searchLink><br /><searchLink fieldCode="AR" term="%22Nguyen%2C+Anh%22">Nguyen, Anh</searchLink><br /><searchLink fieldCode="AR" term="%22Yan%2C+Zhisheng%22">Yan, Zhisheng</searchLink> – Name: TitleSource Label: Source Group: Src Data: ACM Transactions on Multimedia Computing, Communications & Applications; Sep2025, Vol. 21 Issue 9, p1-23, 23p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Live+streaming%22">Live streaming</searchLink><br /><searchLink fieldCode="DE" term="%22Streaming+video+%26+television%22">Streaming video & television</searchLink><br /><searchLink fieldCode="DE" term="%22Client%2Fserver+computing+equipment%22">Client/server computing equipment</searchLink><br /><searchLink fieldCode="DE" term="%22Consumption+%28Economics%29%22">Consumption (Economics)</searchLink><br /><searchLink fieldCode="DE" term="%22Cameras%22">Cameras</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Deep learning (DL)-based compression has achieved outstanding performance compared to traditional compression. However, due to the vulnerability of adversarial attacks on DL models, understanding the security of DL-based compression is crucial. Previous attacks have demonstrated the feasibility of failing DL-based compression models in the digital domain. However, these attacks rely on perfect digital modification of the whole image and internal access to camera/server files, preventing their usage in the physical world where such assumptions do not hold. In this article, we unveil the first physical adversarial attack targeting DL-based compression in the context of live video streaming. The proposed attack, namely CamHack, places a small-sized physical patch in the visual scene covered by the live camera to manipulate the bitrate of compressed content and disrupt live streaming. The patch is crafted to address color and geometric transformations in diverse streaming scenes while remaining inconspicuous. Extensive experiments in various streaming scenes and network conditions show that CamHack increases bit consumption by 276.58%, 384.74%, and 942.28% over the clean scene without a patch on three representative victim models. CamHack is also robust under various practical impacts such as patch location, lighting conditions, and patch size. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of ACM Transactions on Multimedia Computing, Communications & Applications is the property of Association for Computing Machinery and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=188146297 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1145/3750047 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 23 StartPage: 1 Subjects: – SubjectFull: Live streaming Type: general – SubjectFull: Streaming video & television Type: general – SubjectFull: Client/server computing equipment Type: general – SubjectFull: Consumption (Economics) Type: general – SubjectFull: Cameras Type: general Titles: – TitleFull: A Patch Can Disrupt Live Video Streaming: Physical Adversarial Attacks on Deep Learning Compression. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Yang, Yuqing – PersonEntity: Name: NameFull: Nguyen, Anh – PersonEntity: Name: NameFull: Yan, Zhisheng IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 15516857 Numbering: – Type: volume Value: 21 – Type: issue Value: 9 Titles: – TitleFull: ACM Transactions on Multimedia Computing, Communications & Applications Type: main |
| ResultId | 1 |