# Round Trip Translation Defence against Large Language Model Jailbreaking Attacks

arXiv: https://arxiv.org/abs/2402.13517 · HTML: https://mlsanity.com/paper/2402.13517/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 6 of 6)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Interpretable Adversarial Perturbation in Input Embedding Space for Text](https://mlsanity.com/paper/1805.02917/) (2018)
- [MathAttack: Attacking Large Language Models Towards Math Solving Ability](https://mlsanity.com/paper/2309.01686/) (2023)
- [Interpretable Adversarial Training for Text](https://mlsanity.com/paper/1905.12864/) (2019)

## Built on by (most cited first, 6 of 6)

- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [Single-pass Detection of Jailbreaking Input in Large Language Models](https://mlsanity.com/paper/2502.15435/) (2025)
- [Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations](https://mlsanity.com/paper/2410.09097/) (2024)
- [AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment](https://mlsanity.com/paper/2410.11283/) (2024)
- [Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs](https://mlsanity.com/paper/2510.01527/) (2025)
- [Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension](https://mlsanity.com/paper/2503.03502/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these attacks at most. To address this issue, we propose the Round Trip Translation (RTT) method, the first algorithm specifically designed to defend against social-engineered attacks on LLMs. RTT paraphrases the adversarial prompt and generalizes the idea conveyed, making it easier for LLMs to detect induced harmful behavior. This method is versatile, lightweight, and transferrable to different LLMs. Our defense successfully mitigated over 70% of Prompt Automatic Iterative Refinement (PAIR) attacks, which is currently the most effective defense to the best of our knowledge. We are also the first to attempt mitigating the MathsAttack and reduced its attack success rate by almost 40%. Our code is publicly available at https://github.com/Cancanxxx/Round_Trip_Translation_Defence This version of the article has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.48550/arXiv.2402.13517 Use of this Accepted Version is subject to the publisher's Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms