Zhiping (Arya) Zhang

Hi, I'm Zhiping (Arya) Zhang

/ʒiː pɪŋ ʒɑŋ/

👂

arya.zhangpika@gmail.com

I'm a researcher,

designer,

maker.

🙌

I'm a first year PhD student at Northeastern University in the Khoury College of Computer Sciences supervised by Prof. Tianshi Li, and also a member of PEACH (Privacy-Enabling AI and Computer-Human interaction) Lab.

My research focuses on developing trustworthy AI systems that support human-AI collaboration for preserving human privacy. I'm particularly interested in:

1) understanding privacy challenges in personal LLM systems;

2) designing AI systems that leverage model capabilities and complement human effort to align AI behavior with individual’s privacy preferences in real-world applications.

In 2019 Dutch Design Week, Eindhoven, credit by Jianli Zhai

In 2024 iF Award Ceremony, Berlin,

credit by Kaixi Zhou

In 2019 Social Robotics Lab, Eindhoven, credit by SociBot

I obtained an M.Sc. from Eindhoven University of Technology in Netherlands, where I was a member of Social Robotics Lab under supervision of Prof. Emilia Barakova. Before that, I earned a First-class Honours B.Eng. (top 1) at the University of Liverpool and Xi'an Jiaotong-Liverpool University, advised by Prof. Martijn ten Bhömer who introduced me to HCI.

I have also been honored to do research in the CompLING Lab at the University of Waterloo, advised by Prof. Freda Shi, and in the Human-Centered AI Lab, advised by Prof. Dakuo Wang.

Before PhD study, I built real-world Human-AI interaction systems in industry, working as a UX researcher and designer at ALIBABA, and later as an AI product manager and creative technologist at FITURE. My landed projects on the market brought tangible benefits to users and have been recognized with top international events:

🏆(2024 IF Design Award, 2023 Red Dot Award, 2020 IF Talent Award, 2018 Dutch Design Week)

I do research.

I conduct mixed-methods research to understand how LLM systems shape human privacy decisions and trust. I build systems and run computational experiments to measure, model, and address these challenges.

My work has identified both model-side and human-side vulnerabilities, including users’ flawed mental models and overtrust in LLM-based systems as key risks, as well as different human behavioral and perceptual patterns that hinder effective human oversight.

CHI

. The advancements of Large Language Models (LLMs) have decentralized the responsibility for the transparency of AI usage. Specifically, LLM users are now encouraged or required to disclose the use of LLM-generated content for varied types of real-world tasks. However, an emerging phenomenon, users’ secret use of LLMs, raises challenges in ensuring end users adhere to the transparency requirement. Our study used mixed-methods with an exploratory survey (125 real-world secret use cases reported) and a controlled experiment among 300 users to investigate the contexts and causes behind the secret use of LLMs. We found that such secretive behavior is often triggered by certain tasks, transcending demographic and personality differences among users. Task types were found to affect users’ intentions to use secretive behavior, primarily through influencing of perceived external judgment regarding LLM usage. Our results yield important insights for future work on designing interventions to encourage more transparent disclosure of LLM/AI use.

Secret Use of Large Language Model (LLM)

Zhiping Zhang, Chenxinran Shen, Bingsheng Yao, Dakuo Wang, and Tianshi Li

In CSCW 2025

PDF

.

CHI

“It’s a Fair Game”, or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents

Zhiping Zhang, Michelle Jia, Hao-Ping (Hank) Lee, Bingsheng Yao, Sauvik Das, Ada Lerner, Dakuo Wang, and Tianshi Li

In CHI Conference on Human Factors in Computing Systems Apr 2024

🎥 .

. The widespread use of Large Language Model (LLM)-based conversational agents (CAs), especially in high-stakes domains, raises many privacy concerns. Building ethical LLM-based CAs that respect user privacy requires an in-depth understanding of the privacy risks that concern users the most. However, existing research, primarily model-centered, does not provide insight into users’ perspectives. To bridge this gap, we analyzed sensitive disclosures in real-world ChatGPT conversations and conducted semi-structured interviews with 19 LLM-based CA users. We found that users are constantly faced with trade-offs between privacy, utility, and convenience when using LLM-based CAs. However, users’ erroneous mental models and the dark patterns in system design limited their awareness and comprehension of the privacy risks. Additionally, the human-like interactions encouraged more sensitive disclosures, which complicated users’ ability to navigate the trade-offs. We discuss practical design guidelines and the needs for paradigmatic shifts to protect the privacy of LLM-based CA users.

PDF

TALK

WEBSITE

CHI

Human-Centered Privacy Research in the Age of Large Language Models

Tianshi Li, Sauvik Das, Hao-Ping (Hank) Lee, Dakuo Wang, Bingsheng Yao and Zhiping Zhang
In CHI Conference on Human Factors in Computing Systems (CHI’24 Companion) Apr 2024

.

. The emergence of large language models (LLMs), and their increased use in user-facing systems, has led to substantial privacy concerns. To date, research on these privacy concerns has been model-centered: exploring how LLMs lead to privacy risks like memorization, or can be used to infer personal characteristics about people from their content. We argue that there is a need for more research focusing on the human aspect of these privacy issues: e.g., research on how design paradigms for LLMs affect users' disclosure behaviors, users' mental models and preferences for privacy controls, and the design of tools, systems, and artifacts that empower end-users to reclaim ownership over their personal data. To build usable, efficient, and privacy-friendly systems powered by these models with imperfect privacy properties, our goal is to initiate discussions to outline an agenda for conducting human-centered research on privacy issues in LLM-powered systems. This Special Interest Group (SIG) aims to bring together researchers with backgrounds in usable security and privacy, human-AI collaboration, NLP, or any other related domains to share their perspectives and experiences on this problem, to help our community establish a collective understanding of the challenges, research opportunities, research methods, and strategies to collaborate with researchers outside of HCI.

PDF

social robot for musical instrument practice

HRI

Robot Role Design for Implementing Social Facilitation Theory in Musical Instruments Practicing

Heqiu Song, Zhiping Zhang, Emilia I. Barakova, Jaap Ham and Panos Markopoulos
In HRI Conference on Human-Robot Interaction 2020

.

. The application of social robots has recently been explored in various types of educational settings including music learning. Earlier research presented evidence that simply the presence of a robot can influence a person’s task performance, confirming social facilitation theory and findings in human-robot interaction. Confirming the evaluation apprehension theory, earlier studies showed that next to a person’s presence, also that person’s social role could influence a user’s performance: the presence of a (non-) evaluative other can influence the user’s motivation and performance differently. To be able to investigate that, researchers need the roles for the robot which is missing now. In the current research, we describe the design of two social roles (i.e., evaluative role and non-evaluative role) of a robot that can have different appearances. For this, we used the SocibotMini: A robot with a projected face, allowing diversity and great flexibility of human-like social cue presentation. An empirical study at a real practice room including 20 participants confirmed that users (i.e., children) evaluated the robot roles as intended. Thereby, the current research provided the robot roles allowing to study whether the presence of social robots in certain social roles can stimulate practicing behavior and suggestions of how such roles can be designed and improved. Future studies can investigate how the presence of a social robot in a certain social role can stimulate children to practice.

PDF

I design and realize.

I believe that good design truly shines when it integrates seamlessly into users' lives, bringing tangible benefits. I enjoy bridging theory with practical needs to create applications that matter. Here are my selected landed projects that had great impact on our users, achieved commercial success, and earned top international awards. I often incorporated the concept of embodied interaction in my designs, enabling technology such as AI to benefit users.