Lune

ACL Findings2025

MEGen: Generative Backdoor into Large Language Models via Model Editing

Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang, Hai Zhao, Yun Li, Qianren Wang

Abstract

Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs. Traditional backdoor injection methods are primarily limited to yes-or-no discriminative tasks, leading users to underestimate the potential risks of backdoored LLMs. Given the inherently generative nature of LLMs, this paper reveals that a generative backdoor injected into LLMs can expose the true safety risks in their applications. We propose an editing-based generative backdoor, named MEGen, aiming to expand the backdoor to generative tasks in a unified format of any text-to any text, leading to natural generations with a specific intention. Experiments show that MEGen achieves a high attack success rate by adjusting only a small set of local parameters with few-shot samples. Notably, we show that the backdoored model, when triggered, can freely output preset dangerous information while completing downstream tasks. Our work highlights that MEGen enables backdoors in LLMs to exhibit generative capabilities, causing potential safety risks by altering the generative style. The code is available at https://github.com/MonoQ- hub/MEGen.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Locating and Editing Factual Associations in GPT cites Language Models are Few-Shot Learners
  • Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Language Models are Few-Shot Learners
  • ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context Illumination cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ICLScan: Detecting Backdoors in Black-Box Large Language Models via Targeted In-context IlluminationXiaoyi Pang, Xuanyi Hao, Song Guo, Qi Luo et al.NeurIPS 2025 · 7 citations

Builds on23

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
  3. QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke ZettlemoyerNeurIPS 2023 · 5,863 citations
  4. Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
  5. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherYouliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang et al.ICLR 2024 · 441 citations

Related papers

  1. Injecting Universal Jailbreak Backdoors into LLMs in MinutesZhuowei Chen, Qiannan Zhang, Shichao PeiICLR 2025
  2. BadEdit: Backdooring Large Language Models by Model EditingYanzhou Li, Tianlin Li, Kangjie Chen, Jian Zhang et al.ICLR 2024 · 116 citations
  3. BadAgent: Inserting and Activating Backdoor Attacks in LLM AgentsYifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng QianACL 2024
  4. Instruction Backdoor Attacks Against Customized LLMsRui Zhang, Hongwei Li, Rui Wen, Wenbo Jiang et al.USENIX Security 2024 · 83 citations
  5. When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated ExplanationsHuaizhi Ge, Yiming Li, Qifan Wang, Yongfeng Zhang et al.ACL 2025
Dusk over the sea between two cliffs drawn in fine vertical lines