Alignment Defenses Protect LLMs from Property Inference Attacks Without Retraining
This paper introduces alignment-based defenses to protect Large Language Models (LLMs) from property inference attacks that target sensitive, dataset-level information. Unlike prior methods requiring data access and retraining, this approach uses post-training alignment, adapting RLHF frameworks like DPO and GRPO to modify output distributions. Experiments demonstrate that these alignment strategies effectively mitigate inference attacks while preserving model utility.