Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00335540" target="_blank" >RIV/68407700:21230/19:00335540 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/ICCV.2019.00514" target="_blank" >https://doi.org/10.1109/ICCV.2019.00514</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICCV.2019.00514" target="_blank" >10.1109/ICCV.2019.00514</a>
Alternative languages
Result language
angličtina
Original language name
Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower
Original language description
Access to online visual search engines implies sharing of private user content -- the query images. We introduce the concept of targeted mismatch attack for deep learning based retrieval systems to generate an adversarial image to conceal the query image. The generated image looks nothing like the user intended query, but leads to identical or very similar retrieval results. Transferring attacks to fully unseen networks is challenging. We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction. These include loss functions, for example, for unknown global pooling operation or unknown input resolution by the retrieval system. We evaluate the attacks on standard retrieval benchmarks and compare the results retrieved with the original and adversarial image.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 IEEE International Conference on Computer Vision (ICCV 2019)
ISBN
978-1-7281-4803-8
ISSN
1550-5499
e-ISSN
2380-7504
Number of pages
10
Pages from-to
5036-5045
Publisher name
IEEE Computer Society Press
Place of publication
Los Alamitos
Event location
Seoul
Event date
Oct 27, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—