# DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge Distillation

arXiv: https://arxiv.org/abs/2407.10106 · HTML: https://mlsanity.com/paper/2407.10106/

## Key facts

- Cited by 5 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 33 of its 46 references that are in the map.
- First posted on arXiv 14 Jul 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 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [ERNIE 2.0: A Continual Pre-training Framework for Language Understanding](https://mlsanity.com/paper/1907.12412/) (2019)
- [Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://mlsanity.com/paper/2309.14348/) (2023)
- [From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy](https://mlsanity.com/paper/2307.00691/) (2023)
- [Safety Assessment of Chinese Large Language Models](https://mlsanity.com/paper/2304.10436/) (2023)
- [Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues](https://mlsanity.com/paper/2402.09091/) (2024)
- [Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning](https://mlsanity.com/paper/2402.08416/) (2024)
- [BadPrompt: Backdoor Attacks on Continuous Prompts](https://mlsanity.com/paper/2211.14719/) (2022)
- [LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models](https://mlsanity.com/paper/2306.12420/) (2023)
- [FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2309.05274/) (2023)
- [A Cross-Language Investigation into Jailbreak Attacks in Large Language Models](https://mlsanity.com/paper/2401.16765/) (2024)
- [Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment](https://mlsanity.com/paper/2405.13068/) (2024)

## Built on by (most cited first, 5 of 5)

- [Eliminating Backdoors in Neural Code Models for Secure Code Understanding](https://mlsanity.com/paper/2408.04683/) (2024)
- [Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety](https://mlsanity.com/paper/2602.11157/) (2025)
- [Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2606.00105/) (2026)
- [HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing](https://mlsanity.com/paper/2509.23835/) (2025)
- [Knowledge Graph-Guided Multi-Agent Distillation for Reliable Industrial Question Answering with Datasets](https://mlsanity.com/paper/2510.06240/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a significant concern. This risk necessitates rigorous testing and comprehensive evaluation of LLMs to ensure safe and responsible use. However, extensive testing of LLMs requires substantial computational resources, making it an expensive endeavor. Therefore, exploring cost-saving strategies during the testing phase is crucial to balance the need for thorough evaluation with the constraints of resource availability. To address this, our approach begins by transferring the moderation knowledge from an LLM to a small model. Subsequently, we deploy two distinct strategies for generating malicious queries: one based on a syntax tree approach, and the other leveraging an LLM-based method. Finally, our approach incorporates a sequential filter-test process designed to identify test cases that are prone to eliciting toxic responses. Our research evaluated the efficacy of DistillSeq across four LLMs: GPT-3.5, GPT-4.0, Vicuna-13B, and Llama-13B. In the absence of DistillSeq, the observed attack success rates on these LLMs stood at 31.5% for GPT-3.5, 21.4% for GPT-4.0, 28.3% for Vicuna-13B, and 30.9% for Llama-13B. However, upon the application of DistillSeq, these success rates notably increased to 58.5%, 50.7%, 52.5%, and 54.4%, respectively. This translated to an average escalation in attack success rate by a factor of 93.0% when compared to scenarios without the use of DistillSeq. Such findings highlight the significant enhancement DistillSeq offers in terms of reducing the time and resource investment required for effectively testing LLMs.