Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Yihang Chen

Yihang Chen

10 indexed papers

Recent (6 mo)
7
With code
0
Influential cites
0
Benchmarked
0

Publications per year

10
26

Top categories

AI×8Crypto×7Software Eng.×3Multiagent×1ML×1NLP×1

Frequent co-authors

Su Wang6×
Pin Qian6×
Junxian You5×
Xiaoyuan Wang5×
Lifei Liu4×
Haoran Yu4×

Research Timeline

2026
Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach

The paper proposes AnaFP, a theoretically guided analytical fingerprinting scheme that determines the optimal distance of a model's fingerprint from the decision boundary to ensure both robustness and uniqueness for model ownership protection.

IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness

IrisFP introduces a novel adversarial-example-based framework that generates composite-sample fingerprints near the intersection of multiple decision boundaries, significantly enhancing model ownership verification robustness and uniqueness.

LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization

LiteGuard proposes an efficient task-agnostic model fingerprinting framework that achieves enhanced generalization and significantly reduces computational overhead compared to existing methods like MetaV.

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail to detect over-strong claims.

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail to detect over-strong claims.

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, exploitable security vulnerabilities.

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, exploitable security vulnerabilities.

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unaddressed security vulnerabilities.

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

This paper reinterprets supervised fine-tuning as target distribution design and proposes a new method called Target-SFT that constructs the training objective directly from the desired target distribution.

Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

This paper separates three mechanisms contributing to pipeline safety in multi-agent large language models and introduces a controlled contrast design to evaluate their impact.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CRcs.MAEmpiricalRecentJul 8, 2026

Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

Lifei Liu, Haoran Yu, Xiaochong Jiang, Su Wang +2 more

This paper separates three mechanisms contributing to pipeline safety in multi-agent large language models and introduces a controlled contrast design to evaluate their impact.

View →
cs.LGcs.AIcs.CLEmpirical
Recent
Jun 9, 2026

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

Tong Xie, Yuanhao Ban, Yunqi Hong, Sohyun An +2 more

This paper reinterprets supervised fine-tuning as target distribution design and proposes a new method called Target-SFT that constructs the training objective directly from the desired target distrib…

View →
cs.SEcs.AIcs.CRRecentMay 30, 2026

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

Su Wang, Pin Qian, Yihang Chen, Junxian You +5 more

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

View →
cs.SEcs.AIcs.CRRecentMay 30, 2026

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

Su Wang, Pin Qian, Yihang Chen, Junxian You +5 more

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

View →
cs.SEcs.AIcs.CRRecentMay 30, 2026

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

Su Wang, Pin Qian, Yihang Chen, Junxian You +5 more

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unad…

View →
cs.AIRecentMay 27, 2026

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

Pin Qian, Su Wang, Xiaoyuan Wang, Yihang Chen +6 more

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail…

View →
cs.AIRecentMay 27, 2026

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

Pin Qian, Su Wang, Xiaoyuan Wang, Yihang Chen +6 more

The paper introduces FORCEBENCH, a new stress test designed to evaluate whether cited sources genuinely warrant the strength of a claim, revealing that standard citation evaluation methods often fail…

View →
cs.CRMar 26, 2026

IrisFP: Adversarial-Example-based Model Fingerprinting with Enhanced Uniqueness and Robustness

Ziye Geng, Guang Yang, Yihang Chen, Changqing Luo

IrisFP introduces a novel adversarial-example-based framework that generates composite-sample fingerprints near the intersection of multiple decision boundaries, significantly enhancing model ownershi…

View →
cs.CRMar 26, 2026

LiteGuard: Efficient Task-Agnostic Model Fingerprinting with Enhanced Generalization

Guang Yang, Ziye Geng, Yihang Chen, Changqing Luo

LiteGuard proposes an efficient task-agnostic model fingerprinting framework that achieves enhanced generalization and significantly reduces computational overhead compared to existing methods like Me…

View →
cs.CRcs.AIMar 22, 2026

Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach

Guang Yang, Ziye Geng, Yihang Chen, Changqing Luo

The paper proposes AnaFP, a theoretically guided analytical fingerprinting scheme that determines the optimal distance of a model's fingerprint from the decision boundary to ensure both robustness and…

View →