Yufei Han
14 papers · 2016–2026 · 8 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (33) π Conference Polyglot Β· Silver π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Grand Slam
π
Keyword Champion
(3)
ποΈ
Keyword Collector
(67)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(11)
Learning Types Β· Machine Learning
(9)
Artificial Intelligence
(8)
Core AI
(6)
Core Methods
(5)
Computer Vision
(3)
Deep Learning
(3)
Learning Types Β· Deep Learning
(3)
Optimization & Theory
(3)
Analysis
(2)
Domain-Specific
(2)
Learning Paradigms Β· Artificial Intelligence
(2)
Learning Paradigms Β· Machine Learning
(2)
Processing
(2)
Computer Science
(1)
Keywords
adversarial learning
(3)
evasion attack
(3)
adversarial attack
(3)
backdoor attack
(3)
model poisoning
(2)
reflective surface
(2)
categorical data
(2)
adversarial perturbation
(2)
federated learning
(2)
polarimetric imaging
(2)
large language model
(2)
surface reconstruction
(1)
in-context learning
(1)
agent learning
(1)
evaluation framework
(1)
privacy-preserving learning
(1)
logical reasoning
(1)
reinforcement learning
(1)
neural network optimization
(1)
privacy preservation
(1)
Papers
Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs
AAAI 2026
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study
EMNLP 2025
PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction
ICCV 2025
Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data
ICML 2024
BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning
AAAI 2024
Defending Jailbreak Prompts via In-Context Adversarial Game
EMNLP 2024
NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images
CVPR 2024
Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning
AAAI 2023
Towards Efficient and Domain-Agnostic Evasion Attack with High-Dimensional Categorical Inputs
AAAI 2023
Towards Understanding the Robustness Against Evasion Attack on Categorical Data
ICLR 2022
Characterizing the Evasion Attackability of Multi-label Classifiers
AAAI 2021
Learning to dehaze with polarization
NeurIPS 2021
Robust Federated Learning via Collaborative Machine Teaching
AAAI 2020
Partially Supervised Graph Embedding for Positive Unlabelled Feature Selection
IJCAI 2016