Assessment of large language models in spam text generation and detection capabilities
Mainetti, Lorenzo (A.A. 2023/2024) Assessment of large language models in spam text generation and detection capabilities. Tesi di Laurea in Advanced coding for data analytics, Luiss Guido Carli, relatore Alessio Martino, pp. 42. [Bachelor's Degree Thesis]
|
PDF (Full text)
Download (287kB) | Preview |
Abstract/Index
Fundamentals of large language models. Understanding the foundations of large language models. Potential and risks of LLMs. Evolution of spam detection techniques. Basic spam detection methods. Advanced models using deep learning. Selected LLMs for spam generation. TinyLlama. Phi-2. Mistral. Flan-T5. Aya-101. Selected spam detection models. Bag-of-words spam classifier. BERT-tiny. RoBERTa-base. OTIS. Experimental setup and design. Prompt design for spam generation. Implementation details. Evaluation metrics. Results of LLM-generated spam texts. Performance of spam detection models.
References
Bibliografia: pp. 35-36.
| Thesis Type: | Bachelor's Degree Thesis |
|---|---|
| Institution: | Luiss Guido Carli |
| Degree Program: | Bachelor's Degree Programs > Bachelor's Degree Program in Management and Computer Science, English language (L-18) |
| Chair: | Advanced coding for data analytics |
| Thesis Supervisor: | Martino, Alessio |
| Academic Year: | 2023/2024 |
| Session: | Summer |
| Deposited by: | Alessandro Perfetti |
| Date Deposited: | 26 Nov 2024 09:33 |
| Last Modified: | 26 Nov 2024 09:33 |
| URI: | https://tesi.luiss.it/id/eprint/40408 |
Downloads
Downloads per month over past year
Repository Staff Only
 |
View Item |
