Effective black box adversarial attack with handcrafted kernels
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F23%3AA2402L6D" target="_blank" >RIV/61988987:17310/23:A2402L6D - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-031-43078-7_14" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-43078-7_14</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-43078-7_14" target="_blank" >10.1007/978-3-031-43078-7_14</a>
Alternative languages
Result language
angličtina
Original language name
Effective black box adversarial attack with handcrafted kernels
Original language description
We propose a new, simple framework for crafting adversarial examples for black box attacks. The idea is to simulate the substitution model with a non-trainable model compounded of just one layer of handcrafted convolutional kernels and then train the generator neural network to maximize the distance of the outputs for the original and generated adversarial image. We show that fooling the prediction of the first layer causes the whole network to be fooled and decreases its accuracy on adversarial inputs. Moreover, we do not train the neural network to obtain the first convolutional layer kernels, but we create them using the technique of F-transform. Therefore, our method is very time and resource effective.
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
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14135
ISBN
978-303143077-0
ISSN
03029743
e-ISSN
—
Number of pages
12
Pages from-to
169-180
Publisher name
Springer Cham
Place of publication
—
Event location
Ponta Delgada, Portugal
Event date
Jun 19, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—