Jailbreak in the context of LLM is manipulating the prompt to bypass restrictions set by the service provider.
The 4 common prohibited scenarios (Deng et al., 2024):
<ol>
<li>Illegal usage against law
</li>
<li>Generation of harmful or abusive contents
</li>
<li>Violation of rights and privacy
</li>
<li>Generation of adult contents
</li>
</ol>
<h2 id="heading-reference">Reference</h2>
Deng, G., Liu, Y., Li, Y., Wang, K., Zhang, Y., Li, Z., Wang, H., Zhang, T., &amp; Liu, Y. (2024). MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots. Proceedings 2024 Network and Distributed System Security Symposium. <a target="_blank" href="https://doi.org/10.14722/ndss.2024.24188">https://doi.org/10.14722/ndss.2024.24188</a>

Jailbreak in the context of LLM is manipulating the prompt to bypass restrictions set by the service provider.

The 4 common prohibited scenarios (Deng et al., 2024):

1. Illegal usage against law
    
2. Generation of harmful or abusive contents
    
3. Violation of rights and privacy
    
4. Generation of adult contents
    

## Reference

Deng, G., Liu, Y., Li, Y., Wang, K., Zhang, Y., Li, Z., Wang, H., Zhang, T., & Liu, Y. (2024). MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots. *Proceedings 2024 Network and Distributed System Security Symposium*. [https://doi.org/10.14722/ndss.2024.24188](https://doi.org/10.14722/ndss.2024.24188)

iamsywid

iamsywid

TIL: LLM Jailbreak

Reference