Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

Anonymous

Abstract: Large language models (LLMs) need to undergo safety alignment to ensure safe conversations with humans. However, in this work, we introduce an inference-time attack framework, demonstrating that safety alignment can also unintentionally facilitate harmful outcomes under adversarial manipulation. This framework, named Emulated Disalignment (ED), adversely combines a pair of open-source pre-trained and safety-aligned language models in the output space to produce a harmful language model without any training. Our experiments with ED across three datasets and four model families (Llama-1, Llama-2, Mistral, and Alpaca) show that ED doubles the harmfulness of pre-trained models and outperforms strong baselines, achieving the highest harmful rate in 43 out of 48 evaluation subsets by a large margin. Crucially, our findings highlight the importance of reevaluating the practice of open-sourcing language models even after safety alignment.

Paper Type: long

Research Area: Dialogue and Interactive Systems

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Theory

Languages Studied: English