activity
20242026
collaborators

5 papers

cs.CV2026

Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization

Zidong Zhao, Yihao Huang, Qing Guo +5

As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using…

cs.CV2025

Seeing It Before It Happens: In-Generation NSFW Detection for Diffusion-Based Text-to-Image Models

Fan Yang, Yihao Huang, Jiayi Zhu +4

Diffusion-based text-to-image (T2I) models enable high-quality image generation but also pose significant risks of misuse, particularly in producing not-safe-for-work (NSFW) conten…

cs.CR2025

Beyond the Scope: Security Testing of Permission Management in Team Workspace

Liuhuo Wan, Chuan Yan, Mark Huasong Meng +4

Nowadays team workspaces are widely adopted for multi-user collaboration and digital resource management. To further broaden real-world applications, mainstream team workspaces pla…

cs.CR2025

Assessing Privacy Compliance of Android Third-Party SDKs

Mark Huasong Meng, Chuan Yan, Qing Zhang +5

Third-party Software Development Kits (SDKs) are widely adopted in Android app development, to effortlessly accelerate development pipelines and enhance app functionality. However,…

cs.AI2024

The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap

Yedi Zhang, Yufan Cai, Xinyue Zuo +9

Large Language Models (LLMs) have emerged as a transformative AI paradigm, profoundly influencing daily life through their exceptional language understanding and contextual generat…