Related papers: Evaluating the Effectiveness of OpenAI's Parental …

Children are increasingly using technologies powered by Artificial Intelligence (AI). However, there are growing concerns about privacy risks, particularly for children. Although existing privacy regulations require companies and…

The rapid integration of AI-powered coding assistants into developer workflows has raised significant privacy and trust concerns. As developers entrust proprietary code to services like OpenAI's GPT, Google's Gemini, and GitHub Copilot, the…

Content moderation is a central mechanism through which platforms attempt to balance user engagement with community governance. Yet existing research has largely treated moderation as a uniform intervention, overlooking how moderator…

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models.…

The field of AI Control seeks to develop robust control protocols, deployment safeguards for untrusted AI which may be intentionally subversive. However, existing protocols that rely on weaker monitors to detect unsafe behavior often fail…

The rapid proliferation and deployment of General-Purpose AI (GPAI) models, including large language models (LLMs), present unprecedented challenges for AI supervisory entities. We hypothesize that these entities will need to navigate an…

Safety evaluations of large language models (LLMs) typically report binary outcomes, i.e. attack success rate (ASR), refusal rate, or harmful versus safe classification, which hide how risk changes between prompt and response. We present a…

User-configured chatbots built on top of large language models are increasingly available through centralized marketplaces such as OpenAI's GPT Store. While these platforms enforce usage policies intended to prevent harmful or inappropriate…

AI chatbots are widely used by children and teens today, but they pose significant risks to youth's privacy and safety due to both increasingly personal conversations and potential exposure to unsafe content. While children under 13 are…

Generative AI is rapidly moving from research to deployment, elevating the need for responsible development, evaluation, and governance. We conduct a PRISMA guided review of 232 studies (November 2022 - December 2025), spanning large…

As AI systems become more integrated into daily life, the need for safer and more reliable moderation has never been greater. Large Language Models (LLMs) have demonstrated remarkable capabilities, surpassing earlier models in complexity…

The rapid growth of artificial intelligence (AI) technologies has raised major privacy and ethical concerns. However, existing AI incident taxonomies and guidelines lack grounding in real-world cases, limiting their effectiveness for…

Generative AI tools are increasingly entering academic peer review workflows, raising questions about fairness, accountability, and the legitimacy of evaluative judgment. While these systems promise efficiency gains amid growing reviewer…

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…

Many households include children who use voice personal assistants (VPA) such as Amazon Alexa. Children benefit from the rich functionalities of VPAs and third-party apps but are also exposed to new risks in the VPA ecosystem. In this…

This paper analyzes the community safety guidelines of five text-to-image (T2I) generation platforms and audits five T2I models, focusing on prompts related to the representation of humans in areas that might lead to societal stigma. While…

When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three…

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…

Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to block fine-tuning on overtly harmful data. In this setting,…