Short Bio

Peng Cheng is currently a researcher with the State Key Laboratory of Blockchain and Data Security at Zhejiang University, Hangzhou, China. He received his Ph.D. degree in Computer Science from Lancaster University, Lancaster, UK. He was a visiting researcher at University College Cork, Cork, Ireland, from 2019 to 2020. He was a postdoctoral research associate at the School of Cyber Science and Technology, Zhejiang University, Hangzhou, China. His research interests include audio deepfake detection, speech privacy preservation, and IoT security. Results have been published in renowned international journals and conferences such as Proc. IEEE, CCS, S&P, and WWW. His research was a finalist for the 2019 Black Hat Conference Pwnie Award for Innovative Research.

Research Interests

My research focuses on building trustworthy AI ecosystems by addressing security and privacy challenges in artificial intelligence-generated content and intelligent systems.

AI-Generated Content Security forms the core of my current research, investigating the complete AIGC lifecycle through four pillars: privacy preservation, controllability, authenticity, and compliance. I study the robustness of watermarking systems, develop generalizable deepfake detection frameworks, and explore safeguards against adversarial attacks.

Speech Privacy and Security represents my foundational research area, developing solutions for voice-enabled systems from acoustic-channel attacks to privacy-preserving technologies.

Multimodal Data Privacy and IoT Security extends my research to broader human-computer interaction scenarios, investigating cross-modal vulnerabilities and privacy-preserving technologies. This includes novel acoustic side-channel attacks and comprehensive security frameworks for smart devices, bridging theoretical research with practical implementations.

Recent News

• October 2024: Co-supervised Master’s student won the National Graduate Scholarship (China)
• October 2024: Won National Grand Prize in 19th “Challenge Cup” National Competition as advisor for “Multimodal AI Audit Matrix” project
• June 2024: Started position as tenure-track researcher at State Key Laboratory of Blockchain and Data Security, Zhejiang University
• May 2024: Paper “SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution” accepted at CCS 2024
• February 2024: Paper “ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms Using Linguistic Features” accepted at IEEE S&P 2024
• January 2025: Appointed as Program Committee Member for ACM Web Conference (WWW 2025)
• January 2025: Serving as Special Issue Guest Editor for “Intelligent Voice Security and Defense Technologies”, Journal of Cyber Security

Selected Publications

• Huang, P., Pan, K., Wang, Q., Cheng, P., Lu, L., Ba, Z., Ren, K. “SecHeadset: A Practical Privacy Protection System for Real-time Voice Communication.” Proceedings of the ACM MobiSys 2025.

• Ba, Z., Zhong, J., Lei, J., Cheng, P. (corresponding author), Wang, Q., Qin, Z., Wang, Z., Ren, K. “SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution.” Proceedings of the ACM SIGSAC Conference on Computer and Communications Security (CCS 2024), 1166–1180.

• Ba, Z., Gong, B., Wang, Y., Liu, Y., Cheng, P. (corresponding author), Lin, F., Lu, L., Ren, K. “Indelible ‘Footprints’ of Inaudible Command Injection.” IEEE Transactions on Information Forensics and Security (TIFS), 2024.

• Cheng, P., Wang, Y., Huang, P., Ba, Z., Lin, X., Lin, F., Lu, L., Ren, K. “ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms Using Linguistic Features.” IEEE Symposium on Security and Privacy (SP 2024), 1628–1645.

• Huang, P., Wei, Y., Cheng, P., Ba, Z., Lu, L., Lin, F., Wang, Y., Ren, K. “Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege.” IEEE Transactions on Dependable and Secure Computing (TDSC), 2024.

• Ba, Z., Wen, Q., Cheng, P. (corresponding author), Wang, Y., Lin, F., Lu, L., Liu, Z. “Transferring Audio Deepfake Detection Capability Across Languages.” Proceedings of the ACM Web Conference (WWW 2023), 2033–2044.

• Cheng, P., Wu, Y., Hong, Y., Ba, Z., Lin, F., Lu, L., Ren, K. “UniAP: Protecting Speech Privacy With Non-Targeted Universal Adversarial Perturbations.” IEEE Transactions on Dependable and Secure Computing (TDSC), 21(1), 31–46, 2023.

• Cheng, P., Roedig, U. “Personal Voice Assistant Security and Privacy—A Survey.” Proceedings of the IEEE, 110(4), 476–507, 2022.

For a complete list of publications, please visit my Google Scholar profile.

Professional Services

Editorial Services

• Special Issue Guest Editor: “Intelligent Voice Security and Defense Technologies”, Journal of Cyber Security, 2025

Conference Program Committees

• Program Committee Member: ACM Web Conference (WWW 2025)

Journal Reviewer

• International Journals: Proceedings of the IEEE, ACM Transactions on Internet of Things (TIOT), IEEE Internet of Things Journal (IoT-J)
• Chinese Journals: Journal of Information Network Security

Mentorship & Supervision

• Currently co-supervising 5 Ph.D. students and 5 Master’s students at Zhejiang University
• Successfully mentored 1 Ph.D. student, 5 Master’s students, and 5 undergraduate students to degree completion
• One co-supervised Master’s student won the National Graduate Scholarship (China) in October 2024

Industry Impact

My research has made significant contributions to industry security:

• AI Model Security: Identified vulnerabilities in commercial text-to-image models (Midjourney, Stability.ai) through SurrogatePrompt attack method
• Watermarking Systems: Developed DiffForge method, recognized by Amazon’s Responsible AI Team for identifying critical vulnerabilities
• Open-Source Contributions: ALIF framework adopted by NVIDIA for their official AI security toolkit
• Media Recognition: SonarSnoop research featured in IT media (Motherboard, ZDNet, Sophos) and praised by renowned security experts