# The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes

arXiv: https://arxiv.org/abs/2504.17300 · HTML: https://mlsanity.com/paper/2504.17300/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 43 of its 67 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [A backdoor attack against LSTM-based text classification systems](https://mlsanity.com/paper/1905.12457/) (2019)
- [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://mlsanity.com/paper/2105.12400/) (2021)
- [BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements](https://mlsanity.com/paper/2006.01043/) (2020)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Training Data Influence Analysis and Estimation: A Survey](https://mlsanity.com/paper/2212.04612/) (2022)
- [BackdoorBench: A Comprehensive Benchmark of Backdoor Learning](https://mlsanity.com/paper/2206.12654/) (2022)
- [Adversarial Machine Learning -- Industry Perspectives](https://mlsanity.com/paper/2002.05646/) (2020)
- [Adversarial Examples Make Strong Poisons](https://mlsanity.com/paper/2106.10807/) (2021)
- [Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models](https://mlsanity.com/paper/2103.15543/) (2021)
- [RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models](https://mlsanity.com/paper/2110.07831/) (2021)
- [Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution](https://mlsanity.com/paper/2106.06361/) (2021)
- [Mitigating backdoor attacks in LSTM-based Text Classification Systems by Backdoor Keyword Identification](https://mlsanity.com/paper/2007.12070/) (2020)
- [Reevaluating Adversarial Examples in Natural Language](https://mlsanity.com/paper/2004.14174/) (2020)
- [BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models](https://mlsanity.com/paper/2110.02467/) (2021)
- [A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks](https://mlsanity.com/paper/2206.08514/) (2022)
- [Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks](https://mlsanity.com/paper/1911.10312/) (2019)

## Built on by (most cited first, 2 of 2)

- [Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack](https://mlsanity.com/paper/2607.01702/) (2026)
- [DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning](https://mlsanity.com/paper/2607.01729/) (2026)

## Abstract (arXiv)

Backdoor attacks on text classifiers can cause them to predict a predefined label when a particular "trigger" is present. Prior attacks often rely on triggers that are ungrammatical or otherwise unusual, leading to conspicuous attacks. As a result, human annotators, who play a critical role in curating training data in practice, can easily detect and filter out these unnatural texts during manual inspection, reducing the risk of such attacks. We argue that a key criterion for a successful attack is for text with and without triggers to be indistinguishable to humans. However, prior work neither directly nor comprehensively evaluated attack subtlety and invisibility with human involvement. We bridge the gap by conducting thorough human evaluations to assess attack subtlety. We also propose AttrBkd, consisting of three recipes for crafting subtle yet effective trigger attributes, such as extracting fine-grained attributes from existing baseline backdoor attacks. Our human evaluations find that AttrBkd with these baseline-derived attributes is often more effective (higher attack success rate) and more subtle (fewer instances detected by humans) than the original baseline backdoor attacks, demonstrating that backdoor attacks can bypass detection by being inconspicuous and appearing natural even upon close inspection, while still remaining effective. Our human annotation also provides information not captured by automated metrics used in prior work, and demonstrates the misalignment of these metrics with human judgment.