Song Xia
7 papers · 2024–2026 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(21)
🏆
Grand Slam
👑
Triple Crown
Venues
Top co-authors
Research topics
Machine Learning
(7)
Learning Types · Machine Learning
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI · Artificial Intelligence
(4)
Application Areas
(3)
Learning Types · Deep Learning
(3)
Computer Vision
(2)
Security & Privacy
(2)
Analysis
(2)
Optimization & Theory
(2)
Privacy
(2)
Core AI · Computer Vision
(1)
Core Methods
(1)
Models
(1)
Keywords
adversarial attack
(3)
transferable attack
(2)
foundation model
(2)
adversarial perturbation
(2)
adversarial example
(1)
variational autoencoder
(1)
backdoor attack
(1)
feature obfuscation
(1)
randomized smoothing
(1)
collaborative inference
(1)
poisoning attack
(1)
trigger generation
(1)
privacy protection
(1)
model inversion attack
(1)
discrete cosine transform
(1)
temporal consistency
(1)
segment anything model
(1)
unlearnable example
(1)
image quality assessment
(1)
conditional entropy
(1)
Papers
From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge
AAAI 2026
Backdoor Attacks Against No-Reference Image Quality Assessment Models via a Scalable Trigger
AAAI 2025
MTL-UE: Learning to Learn Nothing for Multi-Task Learning
ICML 2025
Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems
CVPR 2025
Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
ICLR 2024
Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders
ICML 2024
Transferable Adversarial Attacks on SAM and Its Downstream Models
NeurIPS 2024