Zedian Shao

Orcid: 0009-0000-6022-8654

According to our database1, Zedian Shao authored at least 13 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning.
CoRR, May, 2026

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Watermark Robustness and Radioactivity May Be at Odds in Federated Learning.
CoRR, October, 2025

PromptLocate: Localizing Prompt Injection Attacks.
CoRR, October, 2025

A Critical Evaluation of Defenses against Prompt Injection Attacks.
CoRR, May, 2025

EnvInjection: Environmental Prompt Injection Attack to Multi-modal Web Agents.
CoRR, May, 2025

WebInject: Prompt Injection Attack to Web Agents.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment.
Proceedings of the 18th ACM Workshop on Artificial Intelligence and Security, 2025

2024
Making LLMs Vulnerable to Prompt Injection via Poisoning Alignment.
CoRR, 2024

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models.
CoRR, 2024

Refusing Safe Prompts for Multi-modal Large Language Models.
CoRR, 2024

The evolution of detection systems and their application for intelligent transportation systems: From solo to symphony.
Comput. Commun., 2024

Align Before Collaborate: Mitigating Feature Misalignment for Robust Multi-agent Perception.
Proceedings of the Computer Vision - ECCV 2024, 2024


  Loading...