BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

Abstract

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to backdoor attacks, where a pre-defined trigger word in the input text causes model misprediction. Previous NLP backdoor attacks mainly focus on some specific tasks. This makes those attacks less general and applicable to other kinds of NLP models and tasks. In this work, we propose \Name, the first task-agnostic backdoor attack against the pre-trained NLP models. The key feature of our attack is that the adversary does not need prior information about the downstream tasks when implanting the backdoor to the pre-trained model. When this malicious model is released, any downstream models transferred from it will also inherit the backdoor, even after the extensive transfer learning process. We further design a simple yet effective strategy to bypass a state-of-the-art defense. Experimental results indicate that our approach can compromise a wide range of downstream NLP tasks in an effective and stealthy way.

References in corpus (6)

• On the Opportunities and Risks of Foundation Models
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Weight Poisoning Attacks on Pre-trained Models
• Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
• Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
• ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

Cited by in corpus (3)

• Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures
• LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
• A General Framework for Defending Against Backdoor Attacks via Influence Graph