Lune

Profiles2024-2026

Jinghuai Zhang

University of California, Los Angeles

11Papers
1Last author
24Unique co-authors
2First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers11

  1. FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud AttacksAuthor 2 of 8WWW 2026 · 3 citations
  2. When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent SystemsAuthor 4 of 10ICLR 2026 · 3 citations
  3. FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language ModelsAuthor 2 of 6ACL 2026
  4. From Perception to Protection: A Developer-Centered Study of Security and Privacy Threats in Extended Reality (XR)Author 2 of 7NDSS 2026
  5. Tracing Back the Malicious Clients in Poisoning Attacks to Federated LearningAuthor 4 of 4NeurIPS 2025 · 8 citations
  6. VideoEraser: Concept Erasure in Text-to-Video Diffusion ModelsAuthor 2 of 8EMNLP 2025 · 1 citation
  7. CollabEdit: Towards Non-destructive Collaborative Knowledge EditingAuthor 2 of 6ICLR 2025
  8. IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM AgentsAuthor 2 of 7EMNLP 2025
  9. Data Poisoning Based Backdoor Attacks to Contrastive LearningAuthor 1 of 4CVPR 2024 · 12 citations
  10. BadMerging: Backdoor Attacks Against Model MergingAuthor 1 of 6CCS 2024 · 5 citations
  11. Where Have You Been? A Study of Privacy Risk for Point-of-Interest RecommendationAuthor 2 of 6KDD 2024 · 5 citations
Dusk over the sea between two cliffs drawn in fine vertical lines