Ju Jia
6 papers · 2025–2026 · 3 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
⭐
Rising Star
(6)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Application Areas
(3)
Deep Learning
(2)
Natural Language Processing
(1)
Security & Privacy
(1)
Architectures
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Privacy
(1)
Resources & Methods
(1)
Keywords
backdoor attack
(2)
multimodal large language model
(2)
graph neural network
(2)
data poisoning
(1)
domain adaptation
(1)
self-supervised learning
(1)
graph representation learning
(1)
knowledge editing
(1)
autonomous driving
(1)
machine unlearning
(1)
agent communication
(1)
bayesian estimation
(1)
message passing
(1)
privacy aware learning
(1)
knowledge graph
(1)
adversarial attack
(1)
adversarial prompt
(1)
privacy leakage
(1)
robustness evaluation
(1)
adversarial patch attack
(1)
Papers
Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
AAAI 2026
MPAS: Breaking Sequential Constraints of Multi-Agent Communication Topologies via Individual-Epistemic Message Propagation
AAAI 2026
PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology Recovery
AAAI 2026
PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems
AAAI 2026
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
ICCV 2025
SelfPrompt: Autonomously Evaluating LLM Robustness via Domain-Constrained Knowledge Guidelines and Refined Adversarial Prompts
COLING 2025