Exploring Backdoor Attacks against Large Language Model-based Decision Making

R Jiao, S Xie, J Yue, T Sato, L Wang, Y Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have shown significant promise in decision-making tasks
when fine-tuned on specific applications, leveraging their inherent common sense and …

Badchain: Backdoor chain-of-thought prompting for large language models

Z Xiang, F Jiang, Z Xiong, B Ramasubramanian… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting,
particularly when tackling tasks that require systematic reasoning processes. On the other …

Phantom: General Trigger Attacks on Retrieval Augmented Language Generation

H Chaudhari, G Severi, J Abascal, M Jagielski… - arXiv preprint arXiv …, 2024 - arxiv.org
Retrieval Augmented Generation (RAG) expands the capabilities of modern large language
models (LLMs) in chatbot applications, enabling developers to adapt and personalize the …

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

P Cheng, Y Ding, T Ju, Z Wu, W Du, P Yi… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have raised concerns about potential security threats
despite performing significantly in Natural Language Processing (NLP). Backdoor attacks …

A Survey of Backdoor Attacks and Defenses on Large Language Models: Implications for Security Measures

S Zhao, M Jia, Z Guo, L Gan, J Fu, Y Feng… - arXiv preprint arXiv …, 2024 - arxiv.org
The large language models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models

X Li, Y Zhang, R Lou, C Wu, J Wang - arXiv preprint arXiv:2406.05948, 2024 - arxiv.org
Backdoor attacks present significant threats to Large Language Models (LLMs), particularly
with the rise of third-party services that offer API integration and prompt engineering …

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

S Abdali, R Anarfi, CJ Barberan, J He - arXiv preprint arXiv:2403.12503, 2024 - arxiv.org
Large language models (LLMs) have significantly transformed the landscape of Natural
Language Processing (NLP). Their impact extends across a diverse spectrum of tasks …

Backdoor Removal for Generative Large Language Models

H Li, Y Chen, Z Zheng, Q Hu, C Chan, H Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
With rapid advances, generative large language models (LLMs) dominate various Natural
Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' …

Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning

X Wang, T Chen, X Yang, Q Zhang, X Zhao… - arXiv preprint arXiv …, 2024 - arxiv.org
The open-sourcing of large language models (LLMs) accelerates application development,
innovation, and scientific progress. This includes both base models, which are pre-trained …

SECURE: Benchmarking Generative Large Language Models for Cybersecurity Advisory

D Bhusal, MT Alam, L Nguyen, A Mahara… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated potential in cybersecurity applications
but have also caused lower confidence due to problems like hallucinations and a lack of …