Related papers: SkillBot: Identifying Risky Content for Children i…
Intelligent personal assistants (IPAs) are supposed to help us multitask. Yet the impact of IPA use on multitasking is not clearly quantified, particularly in situations where primary tasks are also language based. Using a dual task…
With the recent advancements in intelligent personal assistants (IPAs), their popularity is rapidly increasing when it comes to utilizing Automatic Speech Recognition within households. In this study, we used a Wizard-of-Oz methodology to…
Virtual reality (VR) platforms and apps collect user sensor data, including motion, facial, eye, and hand data, in abstracted form. These data may expose users to unique privacy risks without their knowledge or meaningful awareness, yet the…
Including children's images in datasets has raised ethical concerns, particularly regarding privacy, consent, data protection, and accountability. These datasets, often built by scraping publicly available images from the Internet, can…
This paper presents the design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) a large scale Spoken Language Understanding (SLU) Software Development Kit (SDK) that enables developers to extend the…
Intelligent Personal Assistant (IA), also known as Voice Assistant (VA), has become increasingly popular as a human-computer interaction mechanism. Most smartphones have built-in voice assistants that are granted high privilege, which is…
As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…
Conversational AI systems can engage in unsafe behaviour when handling users' medical queries that can have severe consequences and could even lead to deaths. Systems therefore need to be capable of both recognising the seriousness of…
Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial safety in these settings remains poorly understood and weakly evaluated. We present DialogGuard,…
The pervasiveness of abusive content on the internet can lead to severe psychological and physical harm. Significant effort in Natural Language Processing (NLP) research has been devoted to addressing this problem through abusive content…
Social media bot detection has always been an arms race between advancements in machine learning bot detectors and adversarial bot strategies to evade detection. In this work, we bring the arms race to the next level by investigating the…
AI-powered coding assistant tools have revolutionized the software engineering ecosystem. However, prior work has demonstrated that these tools are vulnerable to poisoning attacks. In a poisoning attack, an attacker intentionally injects…
With the rapid development of online technologies and the widespread usage of mobile phones among children, it is crucial to protect their online safety. Some studies reported that online abuse and incidents negatively affect children's…
Advancements in semiconductor technology have reduced dimensions and cost while improving the performance and capacity of chipsets. In addition, advancement in the AI frameworks and libraries brings possibilities to accommodate more AI at…
Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces…
Children with severe disabilities and complex communication needs face limitations in the usage of access technology (AT) devices. Conventional ATs (e.g., mechanical switches) can be insufficient for nonverbal children and those with…
As large language models (LLMs) have proliferated, disturbing anecdotal reports of negative psychological effects, such as delusions, self-harm, and ``AI psychosis,'' have emerged in global media and legal discourse. However, it remains…
Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to…
Smart voice assistants (SVAs) are embedded in the daily lives of youth, yet their privacy controls often remain opaque and difficult to manage. Through five semi-structured focus groups (N=26) with young Canadians (ages 16-24), we…
As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that…