Jian Lou
21 papers · 2015–2026 · 10 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 ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (32) 🌍 Conference Polyglot · Gold 🏃 Academic Marathon · Half 🧬 Topic Evolution
🗃️
Keyword Collector
(91)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(6)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(15)
Artificial Intelligence
(12)
Core AI
(12)
Deep Learning
(7)
Learning Types · Machine Learning
(7)
Optimization & Theory
(7)
Application Areas
(5)
Learning Types · Deep Learning
(4)
Architectures
(3)
Core Methods
(3)
Computer Vision
(2)
Analysis
(2)
Computer Science
(1)
Healthcare & Medicine
(1)
Natural Language Processing
(1)
Keywords
differential privacy
(4)
adversarial training
(4)
stochastic optimization
(3)
machine unlearning
(3)
adversarial robustness
(3)
adversarial learning
(2)
safety alignment
(2)
certified robustness
(2)
representation learning
(2)
text classification
(1)
natural language processing
(1)
embedding space
(1)
contrastive learning
(1)
information bottleneck
(1)
transfer learning
(1)
text summarization
(1)
non-convex optimization
(1)
text generation
(1)
direct preference optimization
(1)
model robustness
(1)
Papers
Stochastic Universal Adversarial Perturbations with Fixed Optimization Constraint and Ensured High-probability Transferability
AAAI 2026
Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
EMNLP 2025
Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
ICML 2025
Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
ICML 2025
Contrastive Unlearning: A Contrastive Approach to Machine Unlearning
IJCAI 2025
Don’t Say No: Jailbreaking LLM by Suppressing Refusal
ACL 2025
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models
ICML 2025
IGAMT: Privacy-Preserving Electronic Health Record Synthesization with Heterogeneity and Irregularity
AAAI 2024
Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
CVPR 2024
Rapid Plug-in Defenders
NeurIPS 2024
Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-Time Dynamics
AAAI 2024
CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation
NeurIPS 2023
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
NeurIPS 2023
Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective
ICCV 2023
MUter: Machine Unlearning on Adversarially Trained Models
ICCV 2023
Certified Robustness to Word Substitution Attack with Differential Privacy
NAACL 2021
Integer-Arithmetic-Only Certified Robustness for Quantized Neural Networks
ICCV 2021
Private Stochastic Non-convex Optimization with Improved Utility Rates
IJCAI 2021
Efficient Generalized Conditional Gradient with Gradient Sliding for Composite Optimization
IJCAI 2015
Equilibrium Analysis of Multi-Defender Security Games
IJCAI 2015
Proximal Average Approximated Incremental Gradient Method for Composite Penalty Regularized Empirical Risk Minimization
ACML 2015