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

2026-03-15

Technology Category

Natural Language Processing: GenerationMachine Learning: Adversarial Learning & RobustnessMultiagent Systems: Adversarial Agents

Application Category

Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationWeb Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Similar Papers

No similar papers found.