← Search

Qingyuan Zeng

4 accepted papers

2026

Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systems

AAAI 2026technical

With the rise of 3D Gaussian Splatting (3DGS), a variety of digital watermarking techniques, embedding either 1D bitstreams or 2D images, are used for copyright protection. However, the robustness of these watermarking techniques against potential attacks remains underexplored. This paper introduces

Cited by 0SourcePDFScholar
2026

VisionLaw: Inferring Interpretable Intrinsic Dynamics from Visual Observations via Bilevel Optimization

ICLR 2026poster

The intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets. Existing methods have attempted to infer the intrinsic dynamics of objects from visual observations, but generally face…

Cited by 0SourceScholar
2024

Ask, Attend, Attack: An Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models

NeurIPS 2024poster

While image-to-text models have demonstrated significant advancements in various vision-language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on image-to-text models require access to the architecture, gradients, and parameters of the target model, resulting in l…

Cited by 2SourcePDFScholar
2024

Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks

AAAI 2024technical

A plethora of fair graph neural networks (GNNs) have been proposed to promote algorithmic fairness for high-stake real-life contexts. Meanwhile, explainability is generally proposed to help machine learning practitioners debug models by providing human-understandable explanations. However, seldom wo…

Cited by 9SourcePDFScholar