Reference : LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
Security, Reliability and Trust
http://hdl.handle.net/10993/53418
LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
English
Gubri, Martin mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal]
Cordy, Maxime mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal]
Papadakis, Mike mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)]
Traon, Yves Le [> >]
Sen, Koushik [> >]
2022
Computer Vision -- ECCV 2022
Springer Nature Switzerland
603--618
Yes
International
978-3-031-19772-7
EUROPEAN CONFERENCE ON COMPUTER VISION
October 23–27, 2022
[en] adversarial machine learning ; adversarial examples ; deep learning ; Transferability ; Loss Geometry
[en] We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional training epochs with a constant and high learning rate. LGV exploits two geometric properties that we relate to transferability. First, models that belong to a wider weight optimum are better surrogates. Second, we identify a subspace able to generate an effective surrogate ensemble among this wider optimum. Through extensive experiments, we show that LGV alone outperforms all (combinations of) four established test-time transformations by 1.8 to 59.9\% points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples.
http://hdl.handle.net/10993/53418
FnR ; FNR12669767 > Yves Le Traon > STELLAR > Testing Self-learning Systems > 01/09/2019 > 31/08/2022 > 2018

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2207.13129.pdfPreprint arXivAuthor preprint1.76 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.