# LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper

arXiv: https://arxiv.org/abs/2402.15727 · HTML: https://mlsanity.com/paper/2402.15727/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 44 of its 54 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Placed in

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

## Builds on (most cited first, 30 of 44)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://mlsanity.com/paper/2308.07308/) (2023)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2402.05044/) (2024)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots](https://mlsanity.com/paper/2307.08715/) (2023)
- [RAIN: Your Language Models Can Align Themselves without Finetuning](https://mlsanity.com/paper/2309.07124/) (2023)
- [Large Language Models for Code: Security Hardening and Adversarial Testing](https://mlsanity.com/paper/2302.05319/) (2023)
- [Jailbreaking Attack against Multimodal Large Language Model](https://mlsanity.com/paper/2402.02309/) (2024)
- [Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs](https://mlsanity.com/paper/2307.10490/) (2023)
- [JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs](https://mlsanity.com/paper/2402.05668/) (2024)
- [The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts](https://mlsanity.com/paper/2401.13136/) (2024)
- [Fuzz4All: Universal Fuzzing with Large Language Models](https://mlsanity.com/paper/2308.04748/) (2023)

## Built on by (most cited first, 10 of 10)

- [SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner](https://mlsanity.com/paper/2406.05498/) (2024)
- [Jailbreaking and Mitigation of Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2410.15236/) (2024)
- [AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens](https://mlsanity.com/paper/2406.03805/) (2024)
- [Decoupled Alignment for Robust Plug-and-Play Adaptation](https://mlsanity.com/paper/2406.01514/) (2024)
- [Active Attacks: Red-teaming LLMs via Adaptive Environments](https://mlsanity.com/paper/2509.21947/) (2025)
- [Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference](https://mlsanity.com/paper/2407.00075/) (2024)
- [Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond](https://mlsanity.com/paper/2410.18114/) (2024)
- [ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction](https://mlsanity.com/paper/2506.01770/) (2025)
- [SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration](https://mlsanity.com/paper/2603.15397/) (2026)
- [When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs](https://mlsanity.com/paper/2607.24392/) (2026)

## Abstract (arXiv)

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the recent Greedy Coordinate Gradient (GCG) attack, jailbreak template-based attacks such as using "Do-Anything-Now" (DAN), and multilingual jailbreak. In contrast, the defensive side has been relatively less explored. This paper proposes a lightweight yet practical defense called SELFDEFEND, which can defend against all existing jailbreak attacks with minimal delay for jailbreak prompts and negligible delay for normal user prompts. Our key insight is that regardless of the kind of jailbreak strategies employed, they eventually need to include a harmful prompt (e.g., "how to make a bomb") in the prompt sent to LLMs, and we found that existing LLMs can effectively recognize such harmful prompts that violate their safety policies. Based on this insight, we design a shadow stack that concurrently checks whether a harmful prompt exists in the user prompt and triggers a checkpoint in the normal stack once a token of "No" or a harmful prompt is output. The latter could also generate an explainable LLM response to adversarial prompts. We demonstrate our idea of SELFDEFEND works in various jailbreak scenarios through manual analysis in GPT-3.5/4. We also list three future directions to further enhance SELFDEFEND.