LLMs in Cybersecurity: Foundations and Applications
BASIC DATA
course listing
A - main register
course code
ITC8301
course title in Estonian
LLM-id küberturbes: alused ja rakendamine
course title in English
LLMs in Cybersecurity: Foundations and Applications
course volume CP
-
ECTS credits
6.00
to be declared
yes
fully online course
not
assessment form
Graded assessment
teaching semester
autumn
language of instruction
Estonian
English
Study programmes that contain the course
code of the study programme version
course compulsory
IVCM25/26
no
Structural units teaching the course
IT - Department of Software Science
Course description link
Timetable link
View the timetable
Version:
VERSION SPECIFIC DATA
course aims in Estonian
Õppeaine eesmärk on anda üliõpilastele teadmised masinõppe ja suurte keelemudelite (LLM) põhikontseptsioonidest. Aine vältel selgitatakse süvaõppe põhimõtteid ja algoritmide kujundamise aluseid. Samuti käsitletakse LLM-ide praktilisi rakendusi küberturbes, sealhulgas seda, kuidas ohte on võimalik ennetada ja leevendada. Üliõpilased omandavad arusaama baasteadmistest ja oskustest, mis on vajalikud LLM-ide rakendamiseks küberturbe kontekstis ning õpivad hindama nende potentsiaalseid tugevusi ja nõrkusi.
course aims in English
The aim of this course is to provide students with a knowledge of the core concepts of machine learning and large language models (LLMs). This will include an explanation of deep learning principles and algorithm design. The practical applications of LLMs in cyber security will be explained with an examination of how threats can be mitigated. Students will gain an appreciation of the basic skills required to apply LLMs in cybersecurity and their potential strengths and weaknesses.
learning outcomes in the course in Est.
Õppeaine läbinud üliõpilane:
- defineerib ja selgitab masinõppe ning süvaõppe põhikontseptsioone;
- tuvastab suurte keelemudelite (LLM) kasutamise tugevusi ja nõrkuseid küberturbe valdkonnas;
- kirjeldab ja selgitab suurte keelemudelite (LLM) põhikontseptsioone ning nende rakendusi küberturbe valdkonnas;
- rakendab uurimismetoodikaid LLM-ide kasutamiseks küberturbe rakendustes;
- kavandab ja viib rühmatööna läbi projekti, rakendades suurt keelemudelit (LLM) konkreetse küberjulgeoleku probleemi lahendamiseks;
- esitab projekti metoodika, tulemused ja järeldused kirjaliku aruandena ning suulise ettekandena.
learning outcomes in the course in Eng.
After completing this course the student:
- describes and explains the fundamental concepts of machine learning and deep learning;
- identifies the strengths and weaknesses of employing LLMs in cybersecurity;
- describes and explains the fundamental concepts of Large Language Models (LLMs) and their cyber security applications;
- employs research methodologies to apply LLMs in a cybersecurity application;
- plans and carries out a project as a group, applying a large language model (LLM) to solve a specific cybersecurity problem;
- presents the project methodology, results, and conclusions in the form of a written report and an oral presentation.
brief description of the course in Estonian
See 6 EAP mahuga aine koosneb 16-st kahetunnisest loengust. Õppeaine algab põhjaliku ülevaatega masinõppe ja süvaõppe põhialustest, hõlmates algoritmide disaini, mudelite treenimist ja soorituse hindamist. Seejärel käsitletakse suurte keelemudelite (LLM) põhikontseptsioone, nagu treenimine, prompting, peenhäälestus, välistoeline genereerimine ning agendid. Aine süvendab LLM-ide rakendusi turvamonitooringus (nt pahavara analüüs, turvalogide analüüs), turvalisusintsidentide käsitlemises, küberohtude luures, tarkvarakoodi turvakontrollis ja pen-testimises. Üliõpilased osalevad semestri vältel rühmatöös, omandades praktilisi oskusi LLM-ide rakendamisel küberturbe probleemide lahendamisel. Õppeainel puuduvad eeltingimused, kuid masinõppealased teadmised on soovitatavad.
brief description of the course in English
This 6 ECTS course will comprise 16 x 2 hour lectures. It will commence with a comprehensive review of core machine learning and deep learning principles, including algorithm design, model training, and performance evaluation. It will them continue with a detailed explanation of the core LLM concepts including training, prompting, fine-tuning, retrieval augmented generation, and agents. The course will further elaborate on the applications of LLMs in security monitoring (e.g., malware analysis, security log analysis), security incident handling, cyber threat intelligence, software code security review, and penetration testing. Students will engage in a semester-long group project to acquire practical skills about utilizing LLMs in cyber security problems. The course has no prerequisites. However, a background in machine learning would be highly beneficial.
type of assessment in Estonian
Iga üliõpilane täidab kursuse jooksul viis praktilist kodust ülesannet, mis keskenduvad masinõppe, süvaõppe ja suurte keelemudelite (LLM) mudelite praktilisele rakendamisele. Lisaks osalevad üliõpilased rühmatöös, kus viiakse läbi semestriprojekt, mis koosneb järgmistest komponentidest:
1. kirjalik projektikavand, mis kirjeldab projekti ulatust, eesmärke ja uurimiskava;
2. üksikasjalik lõpparuanne, mis dokumenteerib uurimistulemused, rakenduse ja analüüsi;
3. projekti esitlus, mille käigus tutvustatakse klassile tulemusi ja peamisi järeldusi.
type of assessment in English
Each student will complete five hands-on homework assignments throughout the course, focusing on the practical application of machine learning, deep learning and LLM models. In addition, students will participate in a group to conduct a term research project, which includes the following components:
(1) A written project proposal outlining the scope, objectives, and research design,
(2) A detailed final project report documenting findings, implementation, and analysis,
(3) A project presentation to demonstrate outcomes and main findings to the class.
independent study in Estonian
-
independent study in English
-
study literature
Kirjandus: Sellel kursusel puudub konkreetne õpik. Selle asemel tehakse kursuse vältel kättesaadavaks valik teadusartikleid, tehnilisi dokumente ja juhtumiuuringuid.

Study literature: There is no specific textbook for this course. However, various papers/documents will be delivered.
study forms and load
daytime study: weekly hours
2.0
session-based study work load (in a semester):
lectures
2.0
lectures
-
practices
0.0
practices
-
exercises
0.0
exercises
-
lecturer in charge
Hayretdin Bahsi, sihtrahastusega professor (IT - tarkvarateaduse instituut)
type (CBL/PBL)
not specified
LECTURER SYLLABUS INFO
semester of studies
teaching lecturer / unit
language of instruction
Extended syllabus
Course-teacher pairs of the corresponding version are missing!
Course description in Estonian
Course description in English