Shudong Zhang

5 papers · 2024–2026 · 4 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 (16) 🐣 Hot Topic Early Bird

Venues

AAAI (2) CVPR (1) ICML (1) NeurIPS (1)

Top co-authors

Tianwei Zhang (3) Guanlin Li (2) Kangjie Chen (2) Shangwei Guo (2) Zihui Wu (1) Jie Zhang (1) Zhaoxiang Liu (1) Jinhu Fu (1) Haichang Gao (1) Tao Xiang (1)

Research topics

Artificial Intelligence (5) Core AI (5) Machine Learning (2) Computer Vision (1) Deep Learning (1) Application Areas (1) Generation (1) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Models (1) Optimization & Theory (1)

Keywords

vision-language model (3) adversarial attack (2) text-to-image generation (1) model editing (1) safety alignment (1) discrete optimization (1) generative model (1) text-to-image model (1) safety evaluation (1) jailbreak attack (1) federated instruction tuning (1) red teaming (1) multimodal understanding (1) model reliability (1) attack success rate (1) knowledge manipulation (1) activation steering (1) generative model safety (1) large language model (1) causal mediation analysis (1)

Papers

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection CVPR 2026 GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization AAAI 2026 ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs AAAI 2026 TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models ICML 2025 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NeurIPS 2024