paper-with-me

홈 › Papers

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

2024-06-05 · Yifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng Qian

With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt trained LLMs and further fine-tune them on data for the agent task. However, we show that such methods are vulnerable to our proposed backdoor attacks named BadAgent on various agent tasks, where a backdoor can be embedded by fine-tuning on the backdoor data. At test time, the attacker can manipulate the deployed LLM agents to execute harmful operations by showing the trigger in the agent input or environment. To our surprise, our proposed attack methods are extremely robust even after fine-tuning on trustworthy data. Though backdoor attacks have been studied extensively in natural language processing, to the best of our knowledge, we could be the first to study them on LLM agents that are more dangerous due to the permission to use external tools. Our work demonstrates the clear risk of constructing LLM agents based on untrusted LLMs or data. Our code is public at https://github.com/DPamK/BadAgent

📄 PDF Abstract BibTeX arXiv:2406.03007

Code (1)

dpamk/badagent 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

2023-04-01 · Hao Chen, Chen Gong, Yizhe WANG, Xinwen Hou

A backdoor attack allows a malicious user to manipulate the environment or corrupt the training data, thus inserting a backdoor into the trained agent. Such attacks compromise the RL system's reliability, leading to pote…

Backdoor Attackreinforcement-learning

C^2 ATTACK: Towards Representation Backdoor on CLIP via Concept Confusion

2025-03-12 · Lijie Hu, Junchi Liao, Weimin Lyu, Shaopeng Fu 외

Backdoor attacks pose a significant threat to deep learning models, enabling adversaries to embed hidden triggers that manipulate the behavior of the model during inference. Traditional backdoor attacks typically rely on…

Backdoor Attack

Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers

2023-10-28 · Wencong You, Zayd Hammoudeh, Daniel Lowd

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are c…

Augmentation Backdoors

2022-09-29 · Joseph Rance, Yiren Zhao, Ilia Shumailov, Robert Mullins

Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the machine learning pipeline. It is well k…

Data Augmentation

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

2023-05-25 · Xuanli He, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks …