Author

Jinyuan Liu

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Book Open access Aug 2026

Rethinking the Stealthiness of Cryptographically Undetectable Backdoors in Practical RFF Learning

This work proves that the operational validity of the CLWE backdoor critically hinges on assumptions that are incompatible with the realistic RFF learning deployment and analyzes the adversarial robustness of RFF learning models and provides a concrete certified robustness analysis, enabling a deeper security assessmen...

Tianshuo Cong, Pei Li, Hao-Jie Wu et al. · Proceedings of the 32nd ACM... · 0 citations

Preprint Aug 2026

Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

GhostVAE is proposed to plant a stealthy backdoor into the encoder of Variational Autoencoder (VAE), enabling reliable evasion of watermark detection and fundamentally undermines the trustworthiness of semantic watermarking systems.

Jinyuan Liu, Tianshuo Cong, Pei Li et al. · 0 citations

Book Open access Aug 2026

Rethinking the Stealthiness of Cryptographically Undetectable Backdoors in Practical RFF Learning

Random Fourier Features (RFF) learning is a classical technique in scalable data mining. However, at FOCS 2022, Goldwasser et al. proposed a theoretical framework for planting cryptographically undetectable backdoors in RFF learning based on the hardness of the Continuous Learning With Errors (CLWE) problem. Their cons...

Tianshuo Cong, Pei Li, Haojie Wu et al. · Proceedings of the 32nd ACM... · 0 citations