Lune

Profiles2018-2026ORCID 0000-0003-4268-372X

Shouling Ji

Zhejiang University

89Papers
33Last author
178Unique co-authors
0First author
0Solo

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

Recent papers89

  1. FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud AttacksAuthor 8 of 8WWW 2026 · 3 citations
  2. TrojanTO: Action-Level Backdoor Attacks Against Trajectory Optimization ModelsAuthor 6 of 9ICLR 2026 · 3 citations
  3. When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent SystemsAuthor 10 of 10ICLR 2026 · 3 citations
  4. Contextual and Seasonal LSTMs for Time Series Anomaly DetectionAuthor 7 of 7ICLR 2026 · 2 citations
  5. Customization under Fire: Plugin Poisoning in Text-to-Image EcosystemAuthor 8 of 8CCS 2026 · 2 citations
  6. IntraGuard: Committee-Side Defenses Against Review Outsourcing to Commercial ChatbotsAuthor 6 of 6CCS 2026 · 2 citations
  7. LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA SharingAuthor 9 of 9KDD 2026 · 2 citations
  8. "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?Author 10 of 10ACL 2026 · 1 citation
  9. Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement LearningAuthor 7 of 7ICML 2026 · 1 citation
  10. StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt GenerationAuthor 4 of 6ACL 2026 · 1 citation
  11. The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal GuardrailsAuthor 10 of 11KDD 2026 · 1 citation
  12. APT-CGLP: Advanced Persistent Threat Hunting via Contrastive Graph-Language Pre-TrainingAuthor 7 of 7KDD 2026
  13. DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain SkewAuthor 8 of 8AAAI 2026
  14. From "Sure" to "Sorry": Detecting Jailbreak in Large Vision Language Model via JailNeuronsAuthor 7 of 7ICLR 2026
  15. SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled AgentsAuthor 5 of 5ICML 2026
  16. The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor AttacksAuthor 8 of 9KDD 2026
  17. Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based ApplicationsAuthor 3 of 3CCS 2026
  18. Uncovering LLM-Generated Code: A Zero-Shot Synthetic Code Detector via Code RewritingAuthor 6 of 7AAAI 2025 · 21 citations
  19. An Inversion-Based Measure of Memorization for Diffusion ModelsAuthor 7 of 8ICCV 2025 · 5 citations
  20. ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation ModelsAuthor 3 of 8WWW 2025 · 5 citations
  21. PromFuzz: Leveraging LLM-Driven and Bug-Oriented Composite Analysis for Detecting Functional Bugs in Smart ContractsAuthor 9 of 9ASE 2025 · 5 citations
  22. Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice DeepfakesAuthor 7 of 7ACM MM 2025 · 1 citation
  23. Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and AlignmentAuthor 7 of 8EMNLP 2025 · 1 citation
  24. VideoEraser: Concept Erasure in Text-to-Video Diffusion ModelsAuthor 8 of 8EMNLP 2025 · 1 citation
  25. CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP ModelsAuthor 6 of 6NDSS 2025
  26. Firmrca: Towards Post-Fuzzing Analysis on ARM Embedded Firmware with Efficient Event-Based Fault LocalizationAuthor 7 of 7S&P 2025
  27. Focus on Generalization: Improving Adversarial Transferability via Bi-Level Bias MitigationAuthor 6 of 6ACM MM 2025
  28. IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM AgentsAuthor 7 of 7EMNLP 2025
  29. Privacy-Preserving Triangle Counting in Directed GraphsAuthor 4 of 5ICDE 2025
  30. PRSA: Prompt Stealing Attacks against Real-World Prompt ServicesAuthor 9 of 9USENIX Security 2025

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines