Related papers: Evaluating the Effectiveness of OpenAI's Parental …
Generative AI (GenAI) browser assistants integrate powerful capabilities of GenAI in web browsers to provide rich experiences such as question answering, content summarization, and agentic navigation. These assistants, available today as…
With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from…
As conversational AI systems increasingly permeate the socio-emotional realms of human life, they bring both benefits and risks to individuals and society. Despite extensive research on detecting and categorizing harms in AI systems, less…
Artificial intelligence (AI) is rapidly transforming healthcare, enabling fast development of tools like stress monitors, wellness trackers, and mental health chatbots. However, rapid and low-barrier development can introduce risks of bias,…
A series of high-profile tragedies involving companion chatbots has triggered an unusually rapid regulatory response. Several jurisdictions, including Australia, California, and New York, have introduced enforceable regulation, while…
AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for…
Ensuring quality human-AI interaction (HAII) in safety-critical industries is essential. Failure to do so can lead to catastrophic and deadly consequences. Despite this urgency, existing research on HAII is limited, fragmented, and…
Recent years have experienced growing contributions of AI coding agents that assist human developers in various software engineering tasks. However, this growing AI-assisted autonomy raises questions about security and trust. In this paper,…
Coding agents and LLM-powered applications routinely send potentially sensitive content to cloud LLM APIs where it may be logged, retained, used for training, or subpoenaed. Existing privacy tooling focuses on network-level encryption and…
AI powered health chatbot applications are increasingly utilized for personalized healthcare services, yet they pose significant challenges related to user data security and privacy. This study evaluates the effectiveness of automated…
We measure the association between generative AI (GAI) tool adoption and four metrics spanning security operations, information protection, and endpoint management: 1) number of security alerts per incident, 2) probability of security…
Online harassment is a widespread social and public health concern, yet most computational approaches for detecting and addressing harassment focus on publicly visible social media content rather than private messaging environments. Private…
The accelerating deployment of artificial intelligence systems across regulated sectors has exposed critical fragmentation in risk assessment methodologies. A significant "language barrier" currently separates technical security teams, who…
Smart Home Personal Assistants (SPA) are an emerging innovation that is changing the way in which home users interact with the technology. However, there are a number of elements that expose these systems to various risks: i) the open…
Prompt-tuning has received attention as an efficient tuning method in the language domain, i.e., tuning a prompt that is a few tokens long, while keeping the large language model frozen, yet achieving comparable performance with…
Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…
Aggregate analytics over conversational data are increasingly used for safety monitoring, governance, and product analysis in large language model systems. A common practice is to embed conversations, cluster them, and publish short textual…
As AI systems become increasingly integrated into daily life, their potential to exacerbate or trigger severe psychological harms remains poorly understood and inadequately tested. This paper presents a proactive methodology for…
Quantitative Artificial Intelligence (AI) Benchmarks have emerged as fundamental tools for evaluating the performance, capability, and safety of AI models and systems. Currently, they shape the direction of AI development and are playing an…
Following the recent release of various Artificial Intelligence (AI) based Conversation Agents (CAs), adolescents are increasingly using CAs for interactive knowledge discovery on sensitive topics, including mental and sexual health topics.…