Gengrui Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Gengrui Zhang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Hantao Zhao
Southeast University, Nanjing, China
2 shared publications - Hewu Li
Tsinghua University, Beijing, China
2 shared publications - Shuning Zhang
Tsinghua University, Beijing, China
2 shared publications - Xin Yi
Tsinghua University, Beijing, China
2 shared publications - Yibo Meng
Cornell University
2 shared publications - Ziyi Zhang
Southeast University, Nanjing, China and School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, Illinois, USA
2 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (2) , 1-38
The Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos
Applying Vision-Language Models (VLMs) to pervasive personal videos introduces profound privacy risks. This paper addresses the critical yet unexplored inferential privacy threat, specifically the risk of inferring sensitive personal attributes from seemingly benign data. To address this gap, we crowdsourced a dataset of 508 everyday personal videos from 58 individuals, and benchmarked VLM inference capabilities against human performance. Our findings reveal three key insights: (1) VLMs surpass recruited human evaluators in inferential accuracy, analyzing temporal behavioral patterns rather than relying solely on object recognition. (2) Inferential risk is strongly correlated with specific video characteristics and prompting strategies. (3) VLM-driven explanation towards the inference is unreliable, as we observe a disconnect between the model's reasoning and evidential impact, where ubiquitous objects often serve as misleading confounders.
- 15 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 10 (2) , 1-38
Open AccessThe Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos
Applying Vision-Language Models (VLMs) to pervasive personal videos introduces profound privacy risks. This paper addresses the critical yet unexplored inferential privacy threat, specifically the risk of inferring sensitive personal attributes from seemingly benign data. To address this gap, we crowdsourced a dataset of 508 everyday personal videos from 58 individuals, and benchmarked VLM inference capabilities against human performance. Our findings reveal three key insights: (1) VLMs surpass recruited human evaluators in inferential accuracy, analyzing temporal behavioral patterns rather than relying solely on object recognition. (2) Inferential risk is strongly correlated with specific video characteristics and prompting strategies. (3) VLM-driven explanation towards the inference is unreliable, as we observe a disconnect between the model's reasoning and evidential impact, where ubiquitous objects often serve as misleading confounders.
- Open Access
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 20-32
Through Their Eyes: User Perceptions on Sensitive Attribute Inference of Social Media Videos by Visual Language Models
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 20-32
Open AccessThrough Their Eyes: User Perceptions on Sensitive Attribute Inference of Social Media Videos by Visual Language Models