Pozivni injekcijski napadi na velike jezikovne modele : magistrsko delo

Bobnar, Matic

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Pozivni injekcijski napadi na velike jezikovne modele : magistrsko delo
Authors:	ID Bobnar, Matic (Author) ID Karakatič, Sašo (Mentor) More about this mentor...
Files:	MAG_Bobnar_Matic_2025.pdf (2,82 MB) MD5: AF7B7660310E3B3E8821E2CCC74EA5FA
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	V magistrskem delu raziskujemo vlogo velikih jezikovnih modelov v vzponu generativne umetne inteligence. Predstavimo osnovne koncepte, kot so transformerji, žetoni in vektorske reprezentacije, ter opisujemo ključne prednosti, slabosti in izzive z generativnimi modeli. Posebno pozornost namenjamo izzivom varnosti, kot so pozivni injekcijski napadi. Podrobno analiziramo delovanje teh napadov, njihove vrste in predstavimo možne pristope za obrambo pred njimi. V okviru eksperimenta prikazujemo izdelavo spletne ankete, ki implementira različne jezikovne modele. S pomočjo pridobljenih podatkov iz ankete nato analiziramo občutljivost posameznih modelov na različne intenzitete injekcijskih napadov ter preučujemo njihove vplive na uporabniške dimenzije, kot so uporabnost, točnost, razumljivost in relevantnost. Na koncu ugotavljamo, kateri modeli se najbolje odzivajo na napade in predstavljajo najvarnejšo uporabo.
Keywords:	Generativna umetna inteligenca, Generativni modeli, Veliki jezikovni modeli, Pozivni injekcijski napadi, Inženering pozivov
Place of publishing:	Maribor
Place of performance:	Maribor
Publisher:	[M. Bobnar]
Year of publishing:	2025
Number of pages:	1 spletni vir (1 datoteka PDF (XVII, 72 str.))
PID:	20.500.12556/DKUM-91632
UDC:	004.8.056(043.2)
COBISS.SI-ID:	226895619
Publication date in DKUM:	06.02.2025
Views:	566
Downloads:	70
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	21.01.2025

Secondary language

Language:	English
Title:	Prompt injection attacks on large language models
Abstract:	In the master's thesis, we explore the role of large language models in the rise of generative artificial intelligence. We present fundamental concepts such as transformers, tokens, and vector representations, and describe the key advantages, disadvantages, and challenges of generative models. Special attention is given to security challenges, such as prompt injection attacks. We analyze the functioning of these attacks in detail, their types, and propose possible defense approaches. As part of the experiment, we develop an online survey application that implements various language models. Using the data collected from the survey, we analyze the sensitivity of individual models to different intensities of injection attacks and examine their impacts on user dimensions such as usability, accuracy, understandability, and relevance. Finally, we identify which models respond best to the attacks and represent the most secure usage.
Keywords:	Generative artificial intelligence, Generative models, Large language models, Prompt injection attacks, Prompt engeneering

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back