Xiangman Li
Scholar

Xiangman Li

Google Scholar ID: O60TTbgAAAAJ
Electrical and Computer Engineering, Queen's University
Google Scholar↗
Citations & Impact
All-time
Citations
24
 
H-index
3
 
i10-index
0
 
Publications
14
 
Co-authors
0
 
Contact
No contact links provided.
Publications
9 items
SkillShield: Prompt-Space Security Skills for LLM Coding Agents
2026
Cited
0
EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
2026
Cited
0
MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulation
2026
Cited
0
Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
2026
Cited
0
SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
2025
Cited
0
SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
2025
Cited
0
When There Is No Decoder: Removing Watermarks from Stable Diffusion Models in a No-box Setting
2025
Cited
0
Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)