Songzhu Zheng
9 papers · 2020–2025 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(8)
Learning Types · Machine Learning
(7)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Core Methods
(3)
Natural Language Processing
(2)
Architectures
(2)
Security & Privacy
(1)
Application Areas
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Privacy
(1)
Keywords
label noise
(4)
trojan attack
(3)
model security
(3)
adversarial machine learning
(2)
trojan attack detection
(2)
adversarial learning
(2)
noisy label
(2)
attention mechanism
(2)
medical image segmentation
(1)
supervised learning
(1)
natural language processing
(1)
bert model
(1)
adversarial detection
(1)
topological data analysis
(1)
adversarial robustness
(1)
deep neural network
(1)
adversarial attack
(1)
self-supervised learning
(1)
backdoor attack
(1)
noisy label learning
(1)
Papers
PivotAlign: Improve Semi-Supervised Learning by Learning Intra-Class Heterogeneity and Aligning with Pivots
WACV 2025
Task-Agnostic Detector for Insertion-Based Backdoor Attacks
NAACL 2024
Attention-Enhancing Backdoor Attacks Against BERT-based Models
EMNLP 2023
Learning to Segment from Noisy Annotations: A Spatial Correction Approach
ICLR 2023
A Study of the Attention Abnormality in Trojaned BERTs
NAACL 2022
Learning with Feature-Dependent Label Noise: A Progressive Approach
ICLR 2021
Topological Detection of Trojaned Neural Networks
NeurIPS 2021
A Topological Filter for Learning with Label Noise
NeurIPS 2020
Error-Bounded Correction of Noisy Labels
ICML 2020