# Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

arXiv: https://arxiv.org/abs/2501.18280 · HTML: https://mlsanity.com/paper/2501.18280/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 50 of its 59 references that are in the map.
- First posted on arXiv 30 Jan 2025.

## Placed in

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

## Builds on (most cited first, 30 of 50)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [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)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [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)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [DeepInception: Hypnotize Large Language Model to Be Jailbreaker](https://mlsanity.com/paper/2311.03191/) (2023)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)

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

- [Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation](https://mlsanity.com/paper/2507.08020/) (2025)
- [Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB](https://mlsanity.com/paper/2511.11041/) (2025)
- [ShallowJail: Steering Jailbreaks against Large Language Models](https://mlsanity.com/paper/2602.07107/) (2026)
- [Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks](https://mlsanity.com/paper/2511.00346/) (2025)
- [Adaptive Prompt Embedding Optimization for LLM Jailbreaking](https://mlsanity.com/paper/2604.24983/) (2026)

## Abstract (arXiv)

The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards based on text embedding models serve as a fundamental defense. Through testing, we discover that the output distribution of text embedding models is severely biased with a large mean. Inspired by this observation, we propose novel, efficient methods to search for **universal magic words** that attack text embedding models. Universal magic words as suffixes can shift the embedding of any text towards the bias direction, thus manipulating the similarity of any text pair and misleading safeguards. Attackers can jailbreak the safeguards by appending magic words to user prompts and requiring LLMs to end answers with magic words. Experiments show that magic word attacks significantly degrade safeguard performance on JailbreakBench, cause real-world chatbots to produce harmful outputs in full-pipeline attacks, and generalize across input/output texts, models, and languages. To eradicate this security risk, we also propose defense methods against such attacks, which can correct the bias of text embeddings and improve downstream performance in a train-free manner.