Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916415650398208 |
|---|---|
| author | Liu, Qin Mo, Wenjie Tong, Terry Xu, Jiashu Wang, Fei Xiao, Chaowei Chen, Muhao |
| author_facet | Liu, Qin Mo, Wenjie Tong, Terry Xu, Jiashu Wang, Fei Xiao, Chaowei Chen, Muhao |
| contents | The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks, particularly backdoor attacks. By exploiting the potent memorization capacity of LLMs, adversaries can easily inject backdoors into LLMs by manipulating a small portion of training data, leading to malicious behaviors in downstream applications whenever the hidden backdoor is activated by the pre-defined triggers. Moreover, emerging learning paradigms like instruction tuning and reinforcement learning from human feedback (RLHF) exacerbate these risks as they rely heavily on crowdsourced data and human feedback, which are not fully controlled. In this paper, we present a comprehensive survey of emerging backdoor threats to LLMs that appear during LLM development or inference, and cover recent advancement in both defense and detection strategies for mitigating backdoor threats to LLMs. We also outline key challenges in addressing these threats, highlighting areas for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19993 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges Liu, Qin Mo, Wenjie Tong, Terry Xu, Jiashu Wang, Fei Xiao, Chaowei Chen, Muhao Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Systems and Control The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks, particularly backdoor attacks. By exploiting the potent memorization capacity of LLMs, adversaries can easily inject backdoors into LLMs by manipulating a small portion of training data, leading to malicious behaviors in downstream applications whenever the hidden backdoor is activated by the pre-defined triggers. Moreover, emerging learning paradigms like instruction tuning and reinforcement learning from human feedback (RLHF) exacerbate these risks as they rely heavily on crowdsourced data and human feedback, which are not fully controlled. In this paper, we present a comprehensive survey of emerging backdoor threats to LLMs that appear during LLM development or inference, and cover recent advancement in both defense and detection strategies for mitigating backdoor threats to LLMs. We also outline key challenges in addressing these threats, highlighting areas for future research. |
| title | Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges |
| topic | Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2409.19993 |