Yanting Wang
Scholar

Yanting Wang

Google Scholar ID: ClAr4UYAAAAJ
Penn State University
Trustworthy AI
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
16
 
H-index
3
 
i10-index
0
 
Publications
6
 
Co-authors
0
 
Contact
Emailykw5450@psu.eduGitHubOpen ↗
Publications
19 items
Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
2026
Cited
0
JustMem: Just-Enough Memory Access for Long-Term Conversations
2026
Cited
0
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
2026
Cited
0
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
2026
Cited
0
PIArena: A Platform for Prompt Injection Evaluation
2026
Cited
0
AgentWatcher: A Rule-based Prompt Injection Monitor
2026
Cited
0
EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method
2026
Cited
0
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
2026
Cited
0
Resume
Academic Achievements
  • TracLLM: A Generic Framework for Attributing Long Context LLMs, USENIX Security 2025 (equal contribution)
  • TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning, AAAI 2025
  • FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models, IEEE S&P 2024
  • MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models, CVPR 2024
  • Preprint: AttnTrace: Attention-based Context Traceback for Long-Context LLMs, arXiv 2025
  • Preprint: TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models, arXiv 2024
  • Program Committee member for AAAI 2026
  • Reviewer for Pattern Recognition (2025) and TNNLS (2024)