TRust Your GENerator (TRYGEN): Enhancing Out-of-Model Scope Detection

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43973204" target="_blank" >RIV/49777513:23520/24:43973204 - isvavai.cz</a>

Result on the web

<a href="https://www.mdpi.com/2673-2688/5/4/104" target="_blank" >https://www.mdpi.com/2673-2688/5/4/104</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/ai5040104" target="_blank" >10.3390/ai5040104</a>

Result language

angličtina

Original language name

TRust Your GENerator (TRYGEN): Enhancing Out-of-Model Scope Detection

Original language description

Recent research has drawn attention to the ambiguity surrounding the definition and learnability of Out-of-Distribution recognition. Although the original problem remains unsolved, the term “Out-of-Model Scope” detection offers a clearer perspective. The ability to detect Out-of-Model Scope inputs is particularly beneficial in safety-critical applications such as autonomous driving or medicine. By detecting Out-of-Model Scope situations, the system’s robustness is enhanced and it is prevented from operating in unknown and unsafe scenarios. In this paper, we propose a novel approach for Out-of-Model Scope detection that integrates three sources of information: (1) the original input, (2) its latent feature representation extracted by an encoder, and (3) a synthesized version of the input generated from its latent representation. We demonstrate the effectiveness of combining original and synthetically generated inputs to defend against adversarial attacks in the computer vision domain. Our method, TRust Your GENerator (TRYGEN), achieves results comparable to those of other state-of-the-art methods and allows any encoder to be integrated into our pipeline in a plug-and-train fashion. Through our experiments, we evaluate which combinations of the encoder’s features are most effective for discovering Out-of-Model Scope samples and highlight the importance of a compact feature space for training the generator.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

20205 - Automation and control systems

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)

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

AI

ISSN

2673-2688

e-ISSN

2673-2688

Volume of the periodical

5

Issue of the periodical within the volume

4

Country of publishing house

CH - SWITZERLAND

Number of pages

20

Pages from-to

2127-2146

UT code for WoS article

001384211400001

EID of the result in the Scopus database

2-s2.0-85213430436