Can Language Models be Instructed to Protect Personal Information?
Primary Area: societal considerations including fairness, safety, privacy
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: large language model, privacy, safety, redteaming, natural language processing
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: Large multimodal language models have proven transformative in numerous applications.
However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns.
While data leaks should be prevented, it is also crucial to examine the trade-off between the privacy protection and model utility of proposed approaches.
In this paper, we introduce PrivQA --- a multimodal benchmark to assess this privacy/utility trade-off when a model is instructed to protect specific categories of personal information in a simulated scenario.
We also propose a technique to iteratively self-moderate responses, which significantly improves privacy.
However, through a series of red-teaming experiments, we find that adversaries can also easily circumvent these protections with simple jailbreaking methods through textual and/or image inputs.
We believe PrivQA has the potential to support the development of new models with improved privacy protections, as well as the adversarial robustness of these protections. We release the entire PrivQA dataset at [URL removed for review].
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6634
Loading