Towards Safer Chatbots: A Framework for Policy Compliance Evaluation of Custom GPTs

• URL: http://arxiv.org/abs/2502.01436v1
• Date: Mon, 03 Feb 2025 15:19:28 GMT
• Title: Towards Safer Chatbots: A Framework for Policy Compliance Evaluation of Custom GPTs
• Authors: David Rodriguez, William Seymour, Jose M. Del Alamo, Jose Such,
• Abstract summary: We present a framework for the automated evaluation of Custom GPTs against OpenAI's usage policies. We evaluate it through a large-scale study with 782 Custom GPTs across three categories: Romantic, Cybersecurity, and Academic GPTs. The results reveal that 58.7% of the analyzed models exhibit indications of non-compliance, exposing weaknesses in the GPT store's review and approval processes.
• Score: 7.687215328455751
• License:
• Abstract: Large Language Models (LLMs) have gained unprecedented prominence, achieving widespread adoption across diverse domains and integrating deeply into society. The capability to fine-tune general-purpose LLMs, such as Generative Pre-trained Transformers (GPT), for specific tasks has facilitated the emergence of numerous Custom GPTs. These tailored models are increasingly made available through dedicated marketplaces, such as OpenAI's GPT Store. However, their black-box nature introduces significant safety and compliance risks. In this work, we present a scalable framework for the automated evaluation of Custom GPTs against OpenAI's usage policies, which define the permissible behaviors of these systems. Our framework integrates three core components: (1) automated discovery and data collection of models from the GPT store, (2) a red-teaming prompt generator tailored to specific policy categories and the characteristics of each target GPT, and (3) an LLM-as-a-judge technique to analyze each prompt-response pair for potential policy violations. We validate our framework with a manually annotated ground truth, and evaluate it through a large-scale study with 782 Custom GPTs across three categories: Romantic, Cybersecurity, and Academic GPTs. Our manual annotation process achieved an F1 score of 0.975 in identifying policy violations, confirming the reliability of the framework's assessments. The results reveal that 58.7% of the analyzed models exhibit indications of non-compliance, exposing weaknesses in the GPT store's review and approval processes. Furthermore, our findings indicate that a model's popularity does not correlate with compliance, and non-compliance issues largely stem from behaviors inherited from base models rather than user-driven customizations. We believe this approach is extendable to other chatbot platforms and policy domains, improving LLM-based systems safety.

Related papers

• On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective [314.7991906491166]
  Generative Foundation Models (GenFMs) have emerged as transformative tools. Their widespread adoption raises critical concerns regarding trustworthiness across dimensions. This paper presents a comprehensive framework to address these challenges through three key contributions.
  arXiv  Detail & Related papers  (2025-02-20T06:20:36Z)
• Privacy Policy Analysis through Prompt Engineering for LLMs [3.059256166047627]
  PAPEL (Privacy Policy Analysis through Prompt Engineering for LLMs) is a framework harnessing the power of Large Language Models (LLMs) to automate the analysis of privacy policies. It aims to streamline the extraction, annotation, and summarization of information from these policies, enhancing their accessibility and comprehensibility without requiring additional model training. We demonstrate the effectiveness of PAPEL with two applications: (i) annotation and (ii) contradiction analysis.
  arXiv  Detail & Related papers  (2024-09-23T10:23:31Z)
• Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning [62.81324245896717]
  We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-ite convergence guarantees under (weak) gradient domination assumptions. We numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-07-15T14:54:57Z)
• GPT Store Mining and Analysis [4.835306415626808]
  The GPT Store serves as a marketplace for Generative Pre-trained Transformer (GPT) models. This study focuses on the categorization of GPTs by topic, factors influencing GPT popularity, and the potential security risks. Our findings aim to enhance understanding of the GPT ecosystem, providing valuable insights for future research, development, and policy-making in generative AI.
  arXiv  Detail & Related papers  (2024-05-16T16:00:35Z)
• Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs [27.97654690288698]
  We conduct a comprehensive analysis of the security and privacy issues arising from the custom GPT platform by OpenAI. Our systematic examination categorizes potential attack scenarios into three threat models based on the role of the malicious actor. We identify 26 potential attack vectors, with 19 being partially or fully validated in real-world settings.
  arXiv  Detail & Related papers  (2023-12-31T16:49:12Z)
• Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
  Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples. We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
  arXiv  Detail & Related papers  (2023-09-14T03:48:27Z)
• SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning [5.177947445379688]
  This study presents a thorough examination of various Generative Pretrained Transformer (GPT) methodologies in sentiment analysis. Three primary strategies are employed: 1) prompt engineering using the advanced GPT-3.5 Turbo, 2) fine-tuning GPT models, and 3) an inventive approach to embedding classification. The research yields detailed comparative insights among these strategies and individual GPT models, revealing their unique strengths and potential limitations.
  arXiv  Detail & Related papers  (2023-07-16T05:33:35Z)
• DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models [92.6951708781736]
  This work proposes a comprehensive trustworthiness evaluation for large language models with a focus on GPT-4 and GPT-3.5. We find that GPT models can be easily misled to generate toxic and biased outputs and leak private information. Our work illustrates a comprehensive trustworthiness evaluation of GPT models and sheds light on the trustworthiness gaps.
  arXiv  Detail & Related papers  (2023-06-20T17:24:23Z)
• Prompting GPT-3 To Be Reliable [117.23966502293796]
  This work decomposes reliability into four facets: generalizability, fairness, calibration, and factuality. We find that GPT-3 outperforms smaller-scale supervised models by large margins on all these facets.
  arXiv  Detail & Related papers  (2022-10-17T14:52:39Z)
• News Summarization and Evaluation in the Era of GPT-3 [73.48220043216087]
  We study how GPT-3 compares against fine-tuned models trained on large summarization datasets. We show that not only do humans overwhelmingly prefer GPT-3 summaries, prompted using only a task description, but these also do not suffer from common dataset-specific issues such as poor factuality.
  arXiv  Detail & Related papers  (2022-09-26T01:04:52Z)

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.