← Authors

Lingjuan Lyu

85 papers · 2020–2026 · 12 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (12) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🀝 Dynamic Duo (21) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (24) πŸ† Keyword Champion (22) ⚑ Prolific Year (20) ❓ The Questioner (7) πŸ—ƒοΈ Keyword Collector (283) πŸ“ˆ Trend Setter πŸ’Ž Century Club (84) πŸ”₯ Unstoppable (6)

Conferences

NIPS (19) ICML (15) ICLR (11) CVPR (8) IJCAI (8) AAAI (6) ICCV (5) EMNLP (4) ACL (3) ECCV (3) NAACL (2) COLING (1)

Top co-authors

Chen Chen (21) Weiming Zhuang (11) Fangzhao Wu (7) Zhenting Wang (7) Vikash Sehwag (6) Chaochao Chen (6) Xuanli He (6) Yang Zhou (6) Jingtao Li (6) Xingjun Ma (6)

Research topics

Differential Privacy (3) Privacy (2)

Keywords

federated learning (22) model compression (9) backdoor attack (8) knowledge distillation (8) adversarial learning (6) model security (5) privacy preservation (5) machine unlearning (5) adversarial attack (5) differential privacy (5) model extraction (4) distributed learning (4) intellectual property (4) large language model (3) privacy leakage (3) graph neural network (3) domain adaptation (3) natural language processing (3) non-iid datum (3) api security (3)

Papers

Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models AAAI 2026
MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025
Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective AAAI 2025
Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning AAAI 2025
Defending against Indirect Prompt Injection by Instruction Detection EMNLP 2025
MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models ACL 2025
Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning ICML 2025
Enhancing Foundation Models with Federated Domain Knowledge Infusion ICML 2025
Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget CVPR 2025
MLLM-as-a-Judge for Image Safety without Human Labeling CVPR 2025
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI CVPR 2025
Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models CVPR 2025
Argus: A Compact and Versatile Foundation Model for Vision CVPR 2025
Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety CVPR 2025
Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter CVPR 2025
How to Evaluate and Mitigate IP Infringement in Visual Generative AI? ICML 2025
Personalized Federated Learning under Local Supervision ICCV 2025
How to Trace Latent Generative Model Generated Images without Artificial Watermark? ICML 2024
FedMef: Towards Memory-efficient Federated Dynamic Pruning CVPR 2024
A Simple Background Augmentation Method for Object Detection with Diffusion Model ECCV 2024
Finding a needle in a haystack: A Black-Box Approach to Invisible Watermark Detection ECCV 2024
Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention ECCV 2024
PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR ICML 2024
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity ICLR 2024
Detecting, Explaining, and Mitigating Memorization in Diffusion Models ICLR 2024
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning NAACL 2024
Protecting Split Learning by Potential Energy Loss IJCAI 2024
DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models ICLR 2024
FedWon: Triumphing Multi-domain Federated Learning Without Normalization ICLR 2024
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection NIPS 2024
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations NIPS 2024
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning NIPS 2024
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence NIPS 2024
DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release NIPS 2024
Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning ICML 2024
COALA: A Practical and Vision-Centric Federated Learning Platform ICML 2024
Effective Federated Graph Matching ICML 2024
Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting ICML 2023
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? NIPS 2023
UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition NIPS 2023
Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning NIPS 2023
Towards Personalized Federated Learning via Heterogeneous Model Reassembly NIPS 2023
Where Did I Come From? Origin Attribution of AI-Generated Images NIPS 2023
Defending against Backdoor Attacks in Natural Language Generation AAAI 2023
Delving into the Adversarial Robustness of Federated Learning AAAI 2023
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark ACL 2023
GNN-SL: Sequence Labeling Based on Nearest Examples via GNN ACL 2023
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation ICCV 2023
The Perils of Learning From Unlabeled Data: Backdoor Attacks on Semi-supervised Learning ICCV 2023
MAS: Towards Resource-Efficient Federated Multiple-Task Learning ICCV 2023
Towards Robustness Certification Against Universal Perturbations ICLR 2023
MECTA: Memory-Economic Continual Test-Time Model Adaptation ICLR 2023
Deja Vu: Continual Model Generalization for Unseen Domains ICLR 2023
IDEAL: Query-Efficient Data-Free Learning from Black-Box Models ICLR 2023
MocoSFL: enabling cross-client collaborative self-supervised learning ICLR 2023
Fast Federated Machine Unlearning with Nonlinear Functional Theory ICML 2023
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers ICML 2023
Reconstructive Neuron Pruning for Backdoor Defense ICML 2023
Dimension-independent Certified Neural Network Watermarks via Mollifier Smoothing ICML 2023
RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation IJCAI 2023
FedSampling: A Better Sampling Strategy for Federated Learning IJCAI 2023
Reducing Communication for Split Learning by Randomized Top-k Sparsification IJCAI 2023
A Pathway Towards Responsible AI Generated Content IJCAI 2023
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs COLING 2022
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022
Extracted BERT Model Leaks More Information than You Think! EMNLP 2022
Privacy for Free: How does Dataset Condensation Help Privacy? ICML 2022
Accelerated Federated Learning with Decoupled Adaptive Optimization ICML 2022
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark AAAI 2022
DENSE: Data-Free One-Shot Federated Learning NIPS 2022
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling NIPS 2022
Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization NIPS 2022
FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning NIPS 2022
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks NIPS 2022
CalFAT: Calibrated Federated Adversarial Training with Label Skewness NIPS 2022
Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification IJCAI 2022
Data-Free Adversarial Knowledge Distillation for Graph Neural Networks IJCAI 2022
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! NAACL 2021
Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation NIPS 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data NIPS 2021
Federated Model Distillation with Noise-Free Differential Privacy IJCAI 2021
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks ICLR 2021
Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning NIPS 2021
Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness EMNLP 2020