Yanting Wang - RankMe

17 papers A* 4Journal 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	EnsembleSHAP: Faithful and Certifiably Robust Attribution for Random Subspace Method. CoRR Yanting Wang, Jinyuan Jia
2026	J	`jnl`	PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses. CoRR Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia
2025	J	`jnl`	AttnTrace: Attention-based Context Traceback for Long-Context LLMs. CoRR Yanting Wang, Runpeng Geng, Ying Chen, Jinyuan Jia
2025	J	`jnl`	PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization. CoRR Runpeng Geng, Yanting Wang, Chenlong Yin, Minhao Cheng, Ying Chen, Jinyuan Jia
2025	J	`jnl`	PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features. CoRR Wei Zou, Yupei Liu, Yanting Wang, Ying Chen, Neil Gong, Jinyuan Jia
2025	J	`jnl`	SecInfer: Preventing Prompt Injection via Inference-time Scaling. CoRR Yupei Liu, Yanting Wang, Yuqi Jia, Jinyuan Jia, Neil Zhenqiang Gong
2025	J	`jnl`	TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization. CoRR Yanting Wang, Runpeng Geng, Jinghui Chen, Minhao Cheng, Jinyuan Jia
2025	A*	`conf`	TracLLM: A Generic Framework for Attributing Long Context LLMs. USENIX Security Symposium Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia
2025	J	`jnl`	TracLLM: A Generic Framework for Attributing Long Context LLMs. CoRR Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia
2025	A*	`conf`	TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning. AAAI Yupei Liu, Yanting Wang, Jinyuan Jia
2025	J	`jnl`	TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning. CoRR Yupei Liu, Yanting Wang, Jinyuan Jia
2025	J	`jnl`	UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation. CoRR Runpeng Geng, Yanting Wang, Ying Chen, Jinyuan Jia
2024	A*	`conf`	FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models. SP Yanting Wang, Wei Zou, Jinyuan Jia
2024	J	`jnl`	FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models. CoRR Yanting Wang, Wei Zou, Jinyuan Jia
2024	A*	`conf`	MMCert: Provable Defense Against Adversarial Attacks to Multi-Modal Models. CVPR Yanting Wang, Hongye Fu, Wei Zou, Jinyuan Jia
2024	J	`jnl`	MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models. CoRR Yanting Wang, Hongye Fu, Wei Zou, Jinyuan Jia
2024	J	`jnl`	TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models. CoRR Yuzhou Nie, Yanting Wang, Jinyuan Jia, Michael J. De Lucia, Nathaniel D. Bastian, Wenbo Guo, Dawn Song