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

Lingshuang Liu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2Sound×1

Frequent co-authors

Qi Li2×
Jianbing Ni2×
Zelin Zhang1×
Jie Cao1×
Yutong Jin1×

Research Timeline

2026
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribution.

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, finding that current defenses lag behind capability deployment.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 15, 2026

From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI

Zelin Zhang, Qi Li, Jie Cao, Lingshuang Liu +1 more

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

View →
cs.SDcs.CRRecentMay 2, 2026

MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech

Yutong Jin, Qi Li, Lingshuang Liu, Jianbing Ni

MelShield is a robust, in-generation audio watermarking framework that embeds identifiable signals into AI-generated speech in the Mel-spectrogram domain for reliable copyright protection and attribut…

View →