# Backdoor Attacks with Input-unique Triggers in NLP

arXiv: https://arxiv.org/abs/2303.14325 · HTML: https://mlsanity.com/paper/2303.14325/

## Key facts

- Cited by 12 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 44 of its 55 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## 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 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Weight Poisoning Attacks on Pre-trained Models](https://mlsanity.com/paper/2004.06660/) (2020)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Input-Aware Dynamic Backdoor Attack](https://mlsanity.com/paper/2010.08138/) (2020)
- [ONION: A Simple and Effective Defense Against Textual Backdoor Attacks](https://mlsanity.com/paper/2011.10369/) (2020)
- [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)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector](https://mlsanity.com/paper/1804.05810/) (2018)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation](https://mlsanity.com/paper/1808.10307/) (2018)
- [Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning](https://mlsanity.com/paper/2108.13888/) (2021)

## Built on by (most cited first, 12 of 12)

- [Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models](https://mlsanity.com/paper/2305.01219/) (2023)
- [Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples](https://mlsanity.com/paper/2510.07192/) (2025)
- [A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks](https://mlsanity.com/paper/2308.14367/) (2023)
- [Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review](https://mlsanity.com/paper/2309.06055/) (2023)
- [A Survey of Recent Backdoor Attacks and Defenses in Large Language Models](https://mlsanity.com/paper/2406.06852/) (2024)
- [Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2402.12168/) (2024)
- [BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts](https://mlsanity.com/paper/2504.18598/) (2025)
- [Data-centric NLP Backdoor Defense from the Lens of Memorization](https://mlsanity.com/paper/2409.14200/) (2024)
- [Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm](https://mlsanity.com/paper/2509.07287/) (2025)
- [Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models](https://mlsanity.com/paper/2601.06305/) (2026)
- [GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis](https://mlsanity.com/paper/2510.09260/) (2025)
- [MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs](https://mlsanity.com/paper/2605.15172/) (2026)

## Abstract (arXiv)

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems. Existing backdoor attacking systems face two severe issues:firstly, most backdoor triggers follow a uniform and usually input-independent pattern, e.g., insertion of specific trigger words, synonym replacement. This significantly hinders the stealthiness of the attacking model, leading the trained backdoor model being easily identified as malicious by model probes. Secondly, trigger-inserted poisoned sentences are usually disfluent, ungrammatical, or even change the semantic meaning from the original sentence, making them being easily filtered in the pre-processing stage. To resolve these two issues, in this paper, we propose an input-unique backdoor attack(NURA), where we generate backdoor triggers unique to inputs. IDBA generates context-related triggers by continuing writing the input with a language model like GPT2. The generated sentence is used as the backdoor trigger. This strategy not only creates input-unique backdoor triggers, but also preserves the semantics of the original input, simultaneously resolving the two issues above. Experimental results show that the IDBA attack is effective for attack and difficult to defend: it achieves high attack success rate across all the widely applied benchmarks, while is immune to existing defending methods. In addition, it is able to generate fluent, grammatical, and diverse backdoor inputs, which can hardly be recognized through human inspection.