← Back ◬ AI & Machine Learning —

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

arXiv Security Archived Mar 18, 2026 ✓ Full text saved

arXiv:2603.15692v1 Announce Type: new 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 pr

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Cryptography and Security [Submitted on 16 Mar 2026] BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator Ruyi Zhang, Heng Gao, Songlei Jian, Yusong Tan, Haifang Zhou 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. Comments: 5pages, 2 figures Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2603.15692 [cs.CR] (or arXiv:2603.15692v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2603.15692 Focus to learn more Submission history From: Ruyi Zhang [view email] [v1] Mon, 16 Mar 2026 03:31:54 UTC (1,175 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes