Tianyu Du
27 papers · 2023–2026 · 8 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 ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (48) 🤝 Dynamic Duo (12) 💎 Century Club · Bronze
🗃️
Keyword Collector
(112)
❓
The Questioner
(2)
⚡
Prolific Year · Prolific
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(20)
Machine Learning
(19)
Core AI
(18)
Natural Language Processing
(9)
Learning Types · Machine Learning
(9)
Deep Learning
(8)
Application Areas
(7)
Learning Paradigms
(6)
Applications
(5)
Models
(5)
Learning Types · Deep Learning
(4)
Optimization & Theory
(4)
Core Methods
(3)
Resources & Methods
(3)
Security & Privacy
(2)
Keywords
large language model
(7)
adversarial training
(4)
privacy preservation
(3)
vision-language model
(3)
question answering
(3)
backdoor attack
(3)
differential privacy
(2)
adversarial learning
(2)
adversarial defense
(2)
code generation
(2)
diffusion model
(2)
federated learning
(2)
adversarial robustness
(2)
in-context learning
(2)
adversarial attack
(2)
knowledge editing
(1)
self-supervised learning
(1)
text classification
(1)
certified robustness
(1)
transfer learning
(1)
Papers
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
ACL 2026
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
AAAI 2026
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
ACL 2026
DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data
AAAI 2026
FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training
AAAI 2026
HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
AAAI 2026
“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns?
ACL 2026
LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping
AAAI 2026
An Inversion-based Measure of Memorization for Diffusion Models
ICCV 2025
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
ICLR 2025
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
EMNLP 2025
CollabEdit: Towards Non-destructive Collaborative Knowledge Editing
ICLR 2025
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
AAAI 2025
DROWN: Towards Tighter LiRPA-based Robustness Certification
COLING 2025
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
EMNLP 2025
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
ACL 2025
Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
IJCAI 2025
Tool-Planner: Task Planning with Clusters across Multiple Tools
ICLR 2025
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
EMNLP 2025
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis
ACL 2024
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback
ACL 2024
ReMasker: Imputing Tabular Data with Masked Autoencoding
ICLR 2024
SecCoder: Towards Generalizable and Robust Secure Code Generation
EMNLP 2024
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
ICCV 2023
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
NeurIPS 2023
UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation
NeurIPS 2023
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
NeurIPS 2023