Mintong Kang
Scholar

Mintong Kang

Google Scholar ID: oHXw2SAAAAAJ
UIUC
Machine Learning
Google Scholar↗
Citations & Impact
All-time
Citations
1,200
 
H-index
12
 
i10-index
14
 
Publications
19
 
Co-authors
6
list available
Contact
No contact links provided.
Publications
9 items
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
2026
Cited
3
Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
2025
Cited
0
ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
2025
Cited
0
PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
2025
Cited
0
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
2025
Cited
0
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
2025
Cited
0
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidance
2025
Cited
0
AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
arXiv.org · 2024
Cited
15
Resume (English only)
Co-authors
6 total
Bo Li
Bo Li
University of Illinois at Urbana–Champaign
Linyi Li
Linyi Li
Simon Fraser University
Xi Li（李玺）
Xi Li（李玺）
College of Computer Science, Zhejiang University, China;
Alan Yuille
Alan Yuille
Professor of Cognitive Science and Computer Science, Johns Hopkins University
Co-author 5
Co-author 5
Ce Zhang
Ce Zhang
Together AI; University of Chicago