Evaluating the Effectiveness of OpenAI's Parental Control System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ersoz, Kerem, Afroogh, Saleh, Atkinson, David, Jiao, Junfeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910006215966720
author Ersoz, Kerem
Afroogh, Saleh
Atkinson, David
Jiao, Junfeng
author_facet Ersoz, Kerem
Afroogh, Saleh
Atkinson, David
Jiao, Junfeng
contents We evaluate how effectively platform-level parental controls moderate a mainstream conversational assistant used by minors. Our two-phase protocol first builds a category-balanced conversation corpus via PAIR-style iterative prompt refinement over API, then has trained human agents replay/refine those prompts in the consumer UI using a designated child account while monitoring the linked parent inbox for alerts. We focus on seven risk areas -- physical harm, pornography, privacy violence, health consultation, fraud, hate speech, and malware and quantify four outcomes: Notification Rate (NR), Leak-Through (LR), Overblocking (OBR), and UI Intervention Rate (UIR). Using an automated judge (with targeted human audit) and comparing the current backend to legacy variants (GPT-4.1/4o), we find that notifications are selective rather than comprehensive: privacy violence, fraud, hate speech, and malware triggered no parental alerts in our runs, whereas physical harm (highest), pornography, and some health queries produced intermittent alerts. The current backend shows lower leak-through than legacy models, yet overblocking of benign, educational queries near sensitive topics remains common and is not surfaced to parents, revealing a policy-product gap between on-screen safeguards and parent-facing telemetry. We propose actionable fixes: broaden/configure the notification taxonomy, couple visible safeguards to privacy-preserving parent summaries, and prefer calibrated, age-appropriate safe rewrites over blanket refusals.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23062
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluating the Effectiveness of OpenAI's Parental Control System
Ersoz, Kerem
Afroogh, Saleh
Atkinson, David
Jiao, Junfeng
Computers and Society
Cryptography and Security
Software Engineering
We evaluate how effectively platform-level parental controls moderate a mainstream conversational assistant used by minors. Our two-phase protocol first builds a category-balanced conversation corpus via PAIR-style iterative prompt refinement over API, then has trained human agents replay/refine those prompts in the consumer UI using a designated child account while monitoring the linked parent inbox for alerts. We focus on seven risk areas -- physical harm, pornography, privacy violence, health consultation, fraud, hate speech, and malware and quantify four outcomes: Notification Rate (NR), Leak-Through (LR), Overblocking (OBR), and UI Intervention Rate (UIR). Using an automated judge (with targeted human audit) and comparing the current backend to legacy variants (GPT-4.1/4o), we find that notifications are selective rather than comprehensive: privacy violence, fraud, hate speech, and malware triggered no parental alerts in our runs, whereas physical harm (highest), pornography, and some health queries produced intermittent alerts. The current backend shows lower leak-through than legacy models, yet overblocking of benign, educational queries near sensitive topics remains common and is not surfaced to parents, revealing a policy-product gap between on-screen safeguards and parent-facing telemetry. We propose actionable fixes: broaden/configure the notification taxonomy, couple visible safeguards to privacy-preserving parent summaries, and prefer calibrated, age-appropriate safe rewrites over blanket refusals.
title Evaluating the Effectiveness of OpenAI's Parental Control System
topic Computers and Society
Cryptography and Security
Software Engineering
url https://arxiv.org/abs/2601.23062