4 papers
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
Ning Li, Zixuan Guo, Yan Xu +7
Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided…
IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness
Ziye Geng, Guang Yang, Yihang Chen +1
We propose IrisFP, a novel adversarial-example-based model fingerprinting framework that enhances both uniqueness and robustness by leveraging multi-boundary characteristics, multi…
LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization
Guang Yang, Ziye Geng, Yihang Chen +1
Task-agnostic model fingerprinting has recently gained increasing attention due to its ability to provide a universal framework applicable across diverse model architectures and ta…
Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach
Guang Yang, Ziye Geng, Yihang Chen +1
Adversarial-example-based fingerprinting approaches, which leverage the decision boundary characteristics of deep neural networks (DNNs) to craft fingerprints, have proven effectiv…