Guanhong Tao

Identifiers

No identifiers captured yet.

Papers (4)

1. A Sentence Relation-Based Approach to Sanitizing Malicious Instructions cs.CR · 2026 · author #4
2. How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies cs.LG · 2025 · author #3
3. PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models cs.CV · 2025 · author #4
4. Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples cs.LG · 2018 · author #1

Mentions

No mention provenance yet.

Frequent Coauthors

• Daniel S. Brown 2 shared papers
• Akansha Kalra 1 shared papers
• Basavasagar Patil 1 shared papers
• Bo Li 1 shared papers
• Chejian Xu 1 shared papers
• Lingzhi Yuan 1 shared papers
• Melissa Umble 1 shared papers
• Shiqing Ma 1 shared papers
• Soumil Datta 1 shared papers
• Wei Dong 1 shared papers
• Xiangyu Zhang 1 shared papers
• Xiaojun Jia 1 shared papers
• Xinfeng Li 1 shared papers
• Yang Liu 1 shared papers
• Yihao Huang 1 shared papers
• Yingqi Liu 1 shared papers