# Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks

**Type:** Papers  
**Canonical URL:** https://scholariq.org/papers/tricking-llms-into-disobedience-formalizing-analyzing-and-detecting-jailbreaks/

## Facts

| Field | Value |
| --- | --- |
| Author Names | Abhinav Rao,Sachin Vashistha,Atharva Naik,Somak Aditya,Monojit Choudhury |
| Citations | 16 |
| DOI | 10.48550/arxiv.2305.14965 |
| Fields | Computer Science |
| Open Access | true |
| OA Status | green |
| OA URL | https://arxiv.org/pdf/2305.14965 |
| OpenAlex ID | https://openalex.org/W4378465191 |
| Type | preprint |
| Year | 2023 |

## Paper authors

- [Somak Aditya](https://scholariq.org/researchers/somak-aditya/)

## Paper journal

- [arXiv (Cornell University)](https://scholariq.org/journals/arxiv-cornell-university/)

## Paper primary topic

- [Digital and Cyber Forensics](https://scholariq.org/topics/digital-and-cyber-forensics/)

## Paper topics

- [Digital and Cyber Forensics](https://scholariq.org/topics/digital-and-cyber-forensics/)
- [Topic Modeling](https://scholariq.org/topics/topic-modeling/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.