Mingkun Zhang
4 papers · 2024–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Gold
🗺️
Taxonomy Completionist
(14)
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Machine Learning
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Application Areas
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Computer Vision
(1)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Applications · Data Science & Analytics
(1)
Core AI
(1)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Keywords
adversarial robustness
(3)
adversarial defense
(2)
adversarial training
(1)
diffusion model
(1)
vision-language model
(1)
adversarial purification
(1)
zero-shot classification
(1)
generative process
(1)
causal disentanglement
(1)
non-additive perturbation
(1)
robust image classification
(1)
perturbation disentanglement
(1)
neural ranking model
(1)
perturbation invariance
(1)
effectiveness-robustness trade-off
(1)
causal factor
(1)
conditional data generation
(1)
robust optimization
(1)
latent space purification
(1)
information retrieval
(1)
Papers
CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
ICLR 2025
NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
ICCV 2025
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
NeurIPS 2024
Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off
AAAI 2024