# LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

arXiv: https://arxiv.org/abs/2308.07308 · HTML: https://mlsanity.com/paper/2308.07308/

## Key facts

- Cited by 244 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 14 Aug 2023.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [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)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [MusicLM: Generating Music From Text](https://mlsanity.com/paper/2301.11325/) (2023)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning](https://mlsanity.com/paper/2308.00436/) (2023)
- [From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy](https://mlsanity.com/paper/2307.00691/) (2023)
- [Globally-Robust Neural Networks](https://mlsanity.com/paper/2102.08452/) (2021)
- [What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus](https://mlsanity.com/paper/2105.02732/) (2021)
- [Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models](https://mlsanity.com/paper/2307.08487/) (2023)
- [The Threat of Offensive AI to Organizations](https://mlsanity.com/paper/2106.15764/) (2021)
- [Flows: Building Blocks of Reasoning and Collaborating AI](https://mlsanity.com/paper/2308.01285/) (2023)

## Built on by (most cited first, 30 of 244)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://mlsanity.com/paper/2402.08983/) (2024)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey](https://mlsanity.com/paper/2402.09283/) (2024)
- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models](https://mlsanity.com/paper/2310.15140/) (2023)
- [A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models](https://mlsanity.com/paper/2402.13457/) (2024)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://mlsanity.com/paper/2410.10700/) (2024)
- [Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries](https://mlsanity.com/paper/2310.13132/) (2023)
- [FlipAttack: Jailbreak LLMs via Flipping](https://mlsanity.com/paper/2410.02832/) (2024)
- [Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing](https://mlsanity.com/paper/2405.18166/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Intention Analysis Makes LLMs A Good Jailbreak Defender](https://mlsanity.com/paper/2401.06561/) (2024)
- [Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing](https://mlsanity.com/paper/2402.16192/) (2024)
- [On the Role of Attention Heads in Large Language Model Safety](https://mlsanity.com/paper/2410.13708/) (2024)
- [Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses](https://mlsanity.com/paper/2406.01288/) (2024)
- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- [Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training](https://mlsanity.com/paper/2407.09121/) (2024)
- [The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness](https://mlsanity.com/paper/2401.00287/) (2023)

## Abstract (arXiv)

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose LLM Self Defense, a simple approach to defend against these attacks by having an LLM screen the induced responses. Our method does not require any fine-tuning, input preprocessing, or iterative output generation. Instead, we incorporate the generated content into a pre-defined prompt and employ another instance of an LLM to analyze the text and predict whether it is harmful. We test LLM Self Defense on GPT 3.5 and Llama 2, two of the current most prominent LLMs against various types of attacks, such as forcefully inducing affirmative responses to prompts and prompt engineering attacks. Notably, LLM Self Defense succeeds in reducing the attack success rate to virtually 0 using both GPT 3.5 and Llama 2. The code is publicly available at https://github.com/poloclub/llm-self-defense