File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3447548.3467121
- Scopus: eid_2-s2.0-85114914389
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Robust Object Detection Fusion against Deception
Title | Robust Object Detection Fusion against Deception |
---|---|
Authors | |
Keywords | adversarial machine learning ensemble defense object detection |
Issue Date | 2021 |
Citation | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2021, p. 2703-2713 How to Cite? |
Abstract | Deep neural network (DNN) based object detection has become an integral part of numerous cyber-physical systems, perceiving physical environments and responding proactively to real-time events. Recent studies reveal that well-trained multi-task learners like DNN-based object detectors perform poorly in the presence of deception. This paper presents FUSE, a deception-resilient detection fusion approach with three novel contributions. First, we develop diversity-enhanced fusion teaming mechanisms, including diversity-enhanced joint training algorithms, for producing high diversity fusion detectors. Second, we introduce a three-tier detection fusion framework and a graph partitioning algorithm to construct fusion-verified detection outputs through three mutually reinforcing components: objectness fusion, bounding box fusion, and classification fusion. Third but not least, we provide a formal analysis of robustness enhancement by FUSE-protected systems. Extensive experiments are conducted on eleven detectors from three families of detection algorithms on two benchmark datasets. We show that FUSE guarantees strong robustness in mitigating the state-of-the-art deception attacks, including adversarial patches - a form of physical attacks using confined visual distortion. |
Persistent Identifier | http://hdl.handle.net/10722/343518 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chow, Ka Ho | - |
dc.contributor.author | Liu, Ling | - |
dc.date.accessioned | 2024-05-10T09:08:44Z | - |
dc.date.available | 2024-05-10T09:08:44Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2021, p. 2703-2713 | - |
dc.identifier.uri | http://hdl.handle.net/10722/343518 | - |
dc.description.abstract | Deep neural network (DNN) based object detection has become an integral part of numerous cyber-physical systems, perceiving physical environments and responding proactively to real-time events. Recent studies reveal that well-trained multi-task learners like DNN-based object detectors perform poorly in the presence of deception. This paper presents FUSE, a deception-resilient detection fusion approach with three novel contributions. First, we develop diversity-enhanced fusion teaming mechanisms, including diversity-enhanced joint training algorithms, for producing high diversity fusion detectors. Second, we introduce a three-tier detection fusion framework and a graph partitioning algorithm to construct fusion-verified detection outputs through three mutually reinforcing components: objectness fusion, bounding box fusion, and classification fusion. Third but not least, we provide a formal analysis of robustness enhancement by FUSE-protected systems. Extensive experiments are conducted on eleven detectors from three families of detection algorithms on two benchmark datasets. We show that FUSE guarantees strong robustness in mitigating the state-of-the-art deception attacks, including adversarial patches - a form of physical attacks using confined visual distortion. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining | - |
dc.subject | adversarial machine learning | - |
dc.subject | ensemble defense | - |
dc.subject | object detection | - |
dc.title | Robust Object Detection Fusion against Deception | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3447548.3467121 | - |
dc.identifier.scopus | eid_2-s2.0-85114914389 | - |
dc.identifier.spage | 2703 | - |
dc.identifier.epage | 2713 | - |