activity
20242026
most citedRandom Erasing vs. Model Inversion: A Promising Defense or a False Hope?

1 citations · 1 across the 6 of their papers we have counts for

collaborators

9 papers

cs.CV2026

Spatially-Aware Class-Agnostic Object Counting

Robert Wijaya, Md. Tanvir Hossain, Amanda Kau +1

Generalised object counting aims to estimate the number of instances of an arbitrary object category from a single image, but many recent methods can struggle on structurally compl…

cs.CV2026

Mixture of Cognitive Experts in Large Vision-Language Models

Robert Wijaya, Ngai-Man Cheung

Large Vision Language Models (LVLMs) require strong reasoning over both visual and textual input. Recent work suggests that cognitive elements, especially diverse representations a…

cs.LG20261 cited

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?

Viet-Hung Tran, Ngoc-Bao Nguyen, Son T. Mai +4

Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models. While existing defenses primarily concentrate o…

cs.CV2026

Characterizing Detectability in 3DGS Poisoning: A Stage-wise Benchmark

Quoc-Anh Bui-Huynh, Thanh Duc Ngo, Xue Geng +4

3D Gaussian Splatting (3DGS) has rapidly emerged as a leading representation for real-time novel view synthesis, but recent work shows it is vulnerable to diverse poisoning attacks…

cs.LG2026

Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment

Sy-Tuyen Ho, Koh Jun Hao, Ngoc-Bao Nguyen +2

Model Inversion attacks aim to reconstruct information from private training data by exploiting access to a target model. Nearly all recent MI studies evaluate attack success using…

cs.LG2026

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks

Ngoc-Bao Nguyen, Sy-Tuyen Ho, Koh Jun Hao +1

Model inversion (MI) attacks pose significant privacy risks by reconstructing private training data from trained neural networks. While prior studies have primarily examined unimod…