File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICNC47757.2020.9049702
- Scopus: eid_2-s2.0-85083456009
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Cross-Layer Strategic Ensemble Defense Against Adversarial Examples
Title | Cross-Layer Strategic Ensemble Defense Against Adversarial Examples |
---|---|
Authors | |
Issue Date | 2020 |
Citation | 2020 International Conference on Computing, Networking and Communications, ICNC 2020, 2020, p. 456-460 How to Cite? |
Abstract | Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defenses. |
Persistent Identifier | http://hdl.handle.net/10722/343299 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wei, Wenqi | - |
dc.contributor.author | Liu, Ling | - |
dc.contributor.author | Loper, Margaret | - |
dc.contributor.author | Chow, Ka Ho | - |
dc.contributor.author | Gursoy, Emre | - |
dc.contributor.author | Truex, Stacey | - |
dc.contributor.author | Wu, Yanzhao | - |
dc.date.accessioned | 2024-05-10T09:07:01Z | - |
dc.date.available | 2024-05-10T09:07:01Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | 2020 International Conference on Computing, Networking and Communications, ICNC 2020, 2020, p. 456-460 | - |
dc.identifier.uri | http://hdl.handle.net/10722/343299 | - |
dc.description.abstract | Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defenses. | - |
dc.language | eng | - |
dc.relation.ispartof | 2020 International Conference on Computing, Networking and Communications, ICNC 2020 | - |
dc.title | Cross-Layer Strategic Ensemble Defense Against Adversarial Examples | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICNC47757.2020.9049702 | - |
dc.identifier.scopus | eid_2-s2.0-85083456009 | - |
dc.identifier.spage | 456 | - |
dc.identifier.epage | 460 | - |