Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Vojtěch Čermák and Lukáš Adam

Affiliation: Faculty of Electrical Engineering Czech Technical University in Prague Technická 2, Prague, Czech Republic

Keyword(s): Adversarial Examples, Robust Machine Learning, Representation Learning, High-level Features, Intermediate Latent Representation.

Abstract: We propose a novel method for creating adversarial examples. Instead of perturbing pixels, we use an encoder-decoder representation of the input image and perturb intermediate layers in the decoder. This changes the high-level features provided by the generative model. Therefore, our perturbation possesses semantic meaning, such as a longer beak or green tints. We formulate this task as an optimization problem by minimizing the Wasserstein distance between the adversarial and initial images under a misclassification constraint. We employ the projected gradient method with a simple inexact projection. Due to the projection, all iterations are feasible, and our method always generates adversarial images. We perform numerical experiments by fooling MNIST and ImageNet classifiers in both targeted and untargeted settings. We demonstrate that our adversarial images are much less vulnerable to steganographic defence techniques than pixel-based attacks. Moreover, we show that our method modi fies key features such as edges and that defence techniques based on adversarial training are vulnerable to our attacks. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.117.103.79

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Čermák, V. and Adam, L. (2022). Adversarial Examples by Perturbing High-level Features in Intermediate Decoder Layers. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 496-507. DOI: 10.5220/0010892800003116

@conference{icaart22,
author={Vojtěch Čermák and Lukáš Adam},
title={Adversarial Examples by Perturbing High-level Features in Intermediate Decoder Layers},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2022},
pages={496-507},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010892800003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Adversarial Examples by Perturbing High-level Features in Intermediate Decoder Layers
SN - 978-989-758-547-0
IS - 2184-433X
AU - Čermák, V.
AU - Adam, L.
PY - 2022
SP - 496
EP - 507
DO - 10.5220/0010892800003116
PB - SciTePress