14 papers
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
Ke Yang, Olivia Figueira, Umar Iqbal +1
Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI chatbots can use this informat…
Actions Speak Louder Than Chats: Investigating AI Chatbot Age Gating
Olivia Figueira, Pranathi Chamarthi, Tu Le +1
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…
VR ProfiLens: User Profiling Risks in Consumer Virtual Reality Apps
Ismat Jarin, Olivia Figueira, Yu Duan +2
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 ri…
BLINDSPOT: Enabling Bystander-Controlled Privacy Signaling for Camera-Enabled Devices
Jad Al Aaraj, Athina Markopoulou
Camera-equipped mobile devices, such as phones, smart glasses, and AR headsets, pose a privacy challenge for bystanders, who currently lack effective real-time mechanisms to contro…
GaitGuard: Protecting Video-Based Gait Privacy in Mixed Reality
Diana Romero, Athina Markopoulou, Salma Elmalaki
Mixed Reality (MR) systems capture continuous video streams that expose bystanders' and collaborators' gait patterns -- a biometric revealing sensitive attributes including age, ge…
When Kids Mode Isn't For Kids: Investigating TikTok's "Under 13 Experience"
Olivia Figueira, Pranathi Chamarthi, Tu Le +1
TikTok, the social media platform that is popular among children and adolescents, offers a more restrictive "Under 13 Experience" exclusively for young users in the US, also known…