Guowen Xu
16 papers · 2022–2026 · 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 ↓+3 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (31) 🏆 Grand Slam 🗃️ Keyword Collector (85)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(7)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(11)
Artificial Intelligence
(10)
Core AI
(8)
Deep Learning
(7)
Application Areas
(7)
Learning Types · Machine Learning
(6)
Computer Vision
(5)
Learning Types · Deep Learning
(4)
Natural Language Processing
(2)
Security & Privacy
(2)
Analysis
(2)
Learning Paradigms
(2)
Processing
(2)
Computer Science
(1)
Reinforcement Learning
(1)
Keywords
adversarial attack
(4)
backdoor attack
(3)
watermark removal
(2)
neural network
(2)
box-free watermarking
(2)
object detection
(1)
secure computation
(1)
reinforcement learning
(1)
autoregressive generation
(1)
adversarial machine learning
(1)
multi-label classification
(1)
autonomous driving
(1)
face recognition
(1)
bird's eye view
(1)
multi-task learning
(1)
secure multi-party computation
(1)
preference learning
(1)
deep learning
(1)
intellectual property
(1)
model robustness
(1)
Papers
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
AAAI 2026
MartDE: A Privacy-Preserving and Cost-Efficient Evaluation Framework for Data Marketplaces
AAAI 2026
MPMA: Preference Manipulation Attack Against Model Context Protocol
AAAI 2026
Removing Box-Free Watermarks for Image-to-Image Models via Query-Based Reverse Engineering
AAAI 2026
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
CVPR 2026
CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird’s Eye View Perception
AAAI 2025
Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
CVPR 2025
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
ICML 2025
Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented Learning
AAAI 2025
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
ICML 2025
Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
ICLR 2023
Color Backdoor: A Robust Poisoning Attack in Color Space
CVPR 2023
Extracting Robust Models with Uncertain Examples
ICLR 2023
GuardHFL: Privacy Guardian for Heterogeneous Federated Learning
ICML 2023
Improving Adversarial Robustness of 3D Point Cloud Classification Models
ECCV 2022
Iron: Private Inference on Transformers
NeurIPS 2022