Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2412.06181 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917862767067136 |
|---|---|
| author | Li, Bryan Bagchi, Sounak Wang, Zizhan |
| author_facet | Li, Bryan Bagchi, Sounak Wang, Zizhan |
| contents | The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance of LLMs to manipulation through the use of prompt simplification techniques. By increasing the transparency of complex and confusing adversarial prompts, the proposed method enables more reliable detection and prevention of malicious inputs. Our findings attempt to address a critical problem in AI safety and security, providing a foundation for the development of systems able to distinguish harmless inputs from prompts containing malicious intent. As LLMs continue to be used in diverse applications, the importance of such safeguards will only grow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06181 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Adversarial Resistance in LLMs with Recursion Li, Bryan Bagchi, Sounak Wang, Zizhan Cryptography and Security Artificial Intelligence The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance of LLMs to manipulation through the use of prompt simplification techniques. By increasing the transparency of complex and confusing adversarial prompts, the proposed method enables more reliable detection and prevention of malicious inputs. Our findings attempt to address a critical problem in AI safety and security, providing a foundation for the development of systems able to distinguish harmless inputs from prompts containing malicious intent. As LLMs continue to be used in diverse applications, the importance of such safeguards will only grow. |
| title | Enhancing Adversarial Resistance in LLMs with Recursion |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2412.06181 |