Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization

• URL: http://arxiv.org/abs/2305.15008v1
• Date: Wed, 24 May 2023 10:48:05 GMT
• Title: Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization
• Authors: Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu and Fatemehsadat Mireshghallah
• Abstract summary: ChatGPT would retain personally identifiable information (PII) verbatim in 57.4% of cases. We probe ChatGPT's perception of privacy-related policies and mechanisms by directly instructing it to provide compliant outputs.
• Score: 4.01610127647615
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed sensitive, personal information in their prompts, as samples for in-context learning, retrieved records from a database, or as part of the conversation. The information provided in the prompt could directly appear in the output, which might have privacy ramifications if there is sensitive information there. As such, in this paper, we aim to understand the input copying and regurgitation capabilities of these models during inference and how they can be directly instructed to limit this copying by complying with regulations such as HIPAA and GDPR, based on their internal knowledge of them. More specifically, we find that when ChatGPT is prompted to summarize cover letters of a 100 candidates, it would retain personally identifiable information (PII) verbatim in 57.4% of cases, and we find this retention to be non-uniform between different subgroups of people, based on attributes such as gender identity. We then probe ChatGPT's perception of privacy-related policies and privatization mechanisms by directly instructing it to provide compliant outputs and observe a significant omission of PII from output.

Related papers

• Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild [40.57348900292574]
  Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy. We run an extensive, fine-grained analysis on the personal disclosures made by real users to commercial GPT models.
  arXiv  Detail & Related papers  (2024-07-16T07:05:31Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• Unsupervised Sentiment Analysis of Plastic Surgery Social Media Posts [91.3755431537592]
  The massive collection of user posts across social media platforms is primarily untapped for artificial intelligence (AI) use cases. Natural language processing (NLP) is a subfield of AI that leverages bodies of documents, known as corpora, to train computers in human-like language understanding. This study demonstrates that the applied results of unsupervised analysis allow a computer to predict either negative, positive, or neutral user sentiment towards plastic surgery.
  arXiv  Detail & Related papers  (2023-07-05T20:16:20Z)
• FedBot: Enhancing Privacy in Chatbots with Federated Learning [0.0]
  Federated Learning (FL) aims to protect data privacy through distributed learning methods that keep the data in its location. The POC combines Deep Bidirectional Transformer models and federated learning algorithms to protect customer data privacy during collaborative model training. The system is specifically designed to improve its performance and accuracy over time by leveraging its ability to learn from previous interactions.
  arXiv  Detail & Related papers  (2023-04-04T23:13:52Z)
• DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4 [80.36535668574804]
  We develop a novel GPT4-enabled de-identification framework (DeID-GPT") Our developed DeID-GPT showed the highest accuracy and remarkable reliability in masking private information from the unstructured medical text. This study is one of the earliest to utilize ChatGPT and GPT-4 for medical text data processing and de-identification.
  arXiv  Detail & Related papers  (2023-03-20T11:34:37Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)
• Partial sensitivity analysis in differential privacy [58.730520380312676]
  We investigate the impact of each input feature on the individual's privacy loss. We experimentally evaluate our approach on queries over private databases. We also explore our findings in the context of neural network training on synthetic data.
  arXiv  Detail & Related papers  (2021-09-22T08:29:16Z)
• Reinforcement Learning on Encrypted Data [58.39270571778521]
  We present a preliminary, experimental study of how a DQN agent trained on encrypted states performs in environments with discrete and continuous state spaces. Our results highlight that the agent is still capable of learning in small state spaces even in presence of non-deterministic encryption, but performance collapses in more complex environments.
  arXiv  Detail & Related papers  (2021-09-16T21:59:37Z)
• CAPE: Context-Aware Private Embeddings for Private Language Learning [0.5156484100374058]
  Context-Aware Private Embeddings (CAPE) is a novel approach which preserves privacy during training of embeddings. CAPE applies calibrated noise through differential privacy, preserving the encoded semantic links while obscuring sensitive information. Experimental results demonstrate that the proposed approach reduces private information leakage better than either single intervention.
  arXiv  Detail & Related papers  (2021-08-27T14:50:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.