Chang Liu

Orcid: 0009-0005-3997-5264

Affiliations:
  • University of Science and Technology of China, School of Cyber Science and Technology, Hefei, China


According to our database1, Chang Liu authored at least 11 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks.
CoRR, July, 2025

Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks.
CoRR, March, 2025

Synthesizing Glyph Vectors for Practical Information Hiding in Documents.
IEEE Trans. Dependable Secur. Comput., 2025

When Translators Refuse to Translate: A Novel Attack to Speech Translation Systems.
Proceedings of the 34th USENIX Security Symposium, 2025

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024
HiFi-GANw: Watermarked Speech Synthesis via Fine-Tuning of HiFi-GAN.
IEEE Signal Process. Lett., 2024

Detecting Voice Cloning Attacks via Timbre Watermarking.
Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

MuST: Robust Image Watermarking for Multi-Source Tracing.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Watermarking Text Generated by Black-Box Language Models.
CoRR, 2023

AutoStegaFont: Synthesizing Vector Fonts for Hiding Information in Documents.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

DeAR: A Deep-Learning-Based Audio Re-recording Resilient Watermarking.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023


  Loading...