9 papers
Alignment Defends LLMs from Property Inference Attacks
Pengrun Huang, Chhavi Yadav, Ruihan Wu +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-l…
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
Erchi Wang, Pengrun Huang, Eli Chien +4
Differential privacy (DP) has a wide range of applications for protecting data privacy, but designing and verifying DP algorithms requires expert-level reasoning, creating a high b…
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Xinjie Shen, Rongzhe Wei, Peizhi Niu +6
Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increas…
Can We Infer Confidential Properties of Training Data from LLMs?
Pengrun Huang, Chhavi Yadav, Kamalika Chaudhuri +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datas…
Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
Tatsuki Koga, Ruihan Wu, Zhiyuan Zhang +1
With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outs…
Evaluating Deep Unlearning in Large Language Models
Ruihan Wu, Chhavi Yadav, Russ Salakhutdinov +1
Machine unlearning has emerged as an important component in developing safe and trustworthy models. Prior work on fact unlearning in LLMs has mostly focused on removing a specified…