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

Han Fang

5 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5AI×4

Frequent co-authors

Benlong Wu3×
Weiming Zhang3×
Kejiang Chen3×
Nenghai Yu3×
Ee-Chien Chang2×
Mengyao Du1×

Research Timeline

2026
Proof-of-Authorship for Diffusion-based AI Generated Content

The paper proposes a novel proof-of-authorship framework for AI-generated content by cryptographically binding the random seed used in latent diffusion model generation to the author's identity, offering a stronger guarantee than traditional ownership methods.

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents

SnapGuard proposes a lightweight, multimodal method to detect prompt injection attacks in screenshot-based web agents by analyzing visual stability and contrast-polarity textual signals, achieving high accuracy with significantly reduced computational overhead.

Provably Secure Agent Guardrail

The paper introduces a formal, logically constrained framework, ePCA, to secure advanced AI agents by forcing them to translate natural language intentions into first-order logical constraints before execution, achieving provably secure performance.

Provably Secure Agent Guardrail

The paper introduces a formal, logically constrained framework, ePCA, to secure advanced AI agents by forcing them to translate natural language intentions into first-order logical constraints before execution, achieving provably secure performance.

Provably Secure Agent Guardrail

The paper introduces an executable Proof-Constrained Action (ePCA) framework that secures AI agents by forcing them to formalize their intentions into first-order logical constraints, achieving provably secure operation.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CRRecentMay 28, 2026

Provably Secure Agent Guardrail

Benlong Wu, Weiming Zhang, Kejiang Chen, Han Fang +1 more

The paper introduces a formal, logically constrained framework, ePCA, to secure advanced AI agents by forcing them to translate natural language intentions into first-order logical constraints before…

View →
cs.AIcs.CRRecentMay 28, 2026

Provably Secure Agent Guardrail