Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

arXiv:2310.17884v2 Announce Type: replace-cross
Abstract: The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are expected to reason about what to share in their outputs, for what purpose and with whom, within a given context. In this work, we draw attention to the highly critical yet overlooked notion of contextual …

ai assistants arxiv can contextual cs.ai cs.cl cs.cr etc fed home information inputs integrity language language models large llms privacy privacy risks risks secret testing theory types work