# BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator

arXiv: https://arxiv.org/abs/2603.15692 · HTML: https://mlsanity.com/paper/2603.15692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## 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, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [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)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems](https://mlsanity.com/paper/1908.01763/) (2019)
- [FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models](https://mlsanity.com/paper/2410.02761/) (2024)
- [RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models](https://mlsanity.com/paper/2110.07831/) (2021)
- [Composite Backdoor Attacks Against Large Language Models](https://mlsanity.com/paper/2310.07676/) (2023)
- [UNICORN: A Unified Backdoor Trigger Inversion Framework](https://mlsanity.com/paper/2304.02786/) (2023)
- [Rethinking the Reverse-engineering of Trojan Triggers](https://mlsanity.com/paper/2210.15127/) (2022)
- [Contextual Integrity in LLMs via Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2506.04245/) (2025)
- [Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation](https://mlsanity.com/paper/2305.11596/) (2023)
- [BadActs: A Universal Backdoor Defense in the Activation Space](https://mlsanity.com/paper/2405.11227/) (2024)
- [Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots](https://mlsanity.com/paper/2310.18633/) (2023)
- [BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing](https://mlsanity.com/paper/2301.10412/) (2023)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space](https://mlsanity.com/paper/2402.12026/) (2024)
- [BAN: Detecting Backdoors Activated by Adversarial Neuron Noise](https://mlsanity.com/paper/2405.19928/) (2024)
- [LP-DETR: Layer-wise Progressive Relations for Object Detection](https://mlsanity.com/paper/2502.05147/) (2025)
- [Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation](https://mlsanity.com/paper/2505.18556/) (2025)

## Abstract (arXiv)

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of text prevents existing noise-based trigger generator from being applied to nature language processing (NLP). To overcome the limitations, we employ the rich knowledge embedded in large language models (LLMs) and propose a Backdoor defender powered by LLM Trigger Generator, termed BadLLM-TG. It is optimized through prompt-driven reinforcement learning, using the victim model's feedback loss as the reward signal. The generated triggers are then employed to mitigate the backdoor via adversarial training. Experiments show that our method reduces the attack success rate by 76.2% on average, outperforming the second-best defender by 13.7.