Work

Targeted Mismatch Adversarial Attack: Query With a Flower to Retrieve the Tower

Year: 2019

Type: conference-paper

Abstract: 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.

Source: IEEE/CVF International Conference on Computer Vision (ICCV)

DOI: 10.1109/iccv.2019.00514

Authors: Giorgos Tolias, Filip Radenovic, Ondrej Chum

Institution: Czech Technical University in Prague

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Grantová Agentura České Republiky, Research Center for Informatics, Czech Technical University in Prague

Awards: G12500569, G4131035492