# Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

arXiv: https://arxiv.org/abs/2412.03235 · HTML: https://mlsanity.com/paper/2412.03235/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 39 of its 46 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 39)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [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)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)

## Built on by (most cited first, 15 of 15)

- [Adversarial Preference Learning for Robust LLM Alignment](https://mlsanity.com/paper/2505.24369/) (2025)
- [Backtracking for Safety](https://mlsanity.com/paper/2503.08919/) (2025)
- [Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs](https://mlsanity.com/paper/2605.21602/) (2026)
- [Semantic Representation Attack against Aligned Large Language Models](https://mlsanity.com/paper/2509.19360/) (2025)
- [PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits](https://mlsanity.com/paper/2510.17947/) (2025)
- [Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models](https://mlsanity.com/paper/2504.05050/) (2025)
- [BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models](https://mlsanity.com/paper/2504.07997/) (2025)
- [Small Reward Models via Backward Inference](https://mlsanity.com/paper/2602.13551/) (2026)
- [ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack](https://mlsanity.com/paper/2509.25843/) (2025)
- [Reinforcement Learning with Backtracking Feedback](https://mlsanity.com/paper/2602.08377/) (2026)
- [LLM-Agnostic Semantic Representation Attack](https://mlsanity.com/paper/2605.08898/) (2026)
- [Evolving and Detecting Multi-Turn Deception using Geometric Signatures](https://mlsanity.com/paper/2605.27671/) (2026)
- [Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack](https://mlsanity.com/paper/2606.05614/) (2026)
- [Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks](https://mlsanity.com/paper/2608.04286/) (2026)
- [What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis](https://mlsanity.com/paper/2609.19212/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While the large dimensionality of input token space makes it inevitable to find adversarial prompts that can jailbreak these models, we aim to evaluate whether safety fine-tuned LLMs are safe against natural prompts which are semantically related to toxic seed prompts that elicit safe responses after alignment. We surprisingly find that popular aligned LLMs such as GPT-4 can be compromised using naive prompts that are NOT even crafted with an objective of jailbreaking the model. Furthermore, we empirically show that given a seed prompt that elicits a toxic response from an unaligned model, one can systematically generate several semantically related natural prompts that can jailbreak aligned LLMs. Towards this, we propose a method of Response Guided Question Augmentation (ReG-QA) to evaluate the generalization of safety aligned LLMs to natural prompts, that first generates several toxic answers given a seed question using an unaligned LLM (Q to A), and further leverages an LLM to generate questions that are likely to produce these answers (A to Q). We interestingly find that safety fine-tuned LLMs such as GPT-4o are vulnerable to producing natural jailbreak questions from unsafe content (without denial) and can thus be used for the latter (A to Q) step. We obtain attack success rates that are comparable to/ better than leading adversarial attack methods on the JailbreakBench leaderboard, while being significantly more stable against defenses such as Smooth-LLM and Synonym Substitution, which are effective against existing all attacks on the leaderboard.