Peng Cheng

29 papers A* 5A 1Journal 19Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection.
CoRR
Qingyu Liu, Yitao Zhang, Zhongjie Ba, Chao Shuai, Peng Cheng, Tianhang Zheng, Zhibo Wang
2026 A* conf
Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues.
AAAI
Zhongjie Ba, Liang Yi, Peng Cheng, Qingcao Li, Qinglong Wang, Li Lu
2026 J jnl
Divide and Conquer: Multimodal Video Deepfake Detection via Cross-Modal Fusion and Localization.
CoRR
Qingcao Li, Miao He, Liang Yi, Qing Wen, Yitao Zhang, Hongshuo Jin, Peng Cheng, Zhongjie Ba, Li Lu, Kui Ren
2026 J jnl
HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection.
CoRR
Qing Wen, Haohao Li, Zhongjie Ba, Peng Cheng, Miao He, Li Lu, Kui Ren
2026 J jnl
Integrating Path Selection for Symbolic Execution and Variable Selection for Constraint Solving.
ACM Trans. Softw. Eng. Methodol.
Shunkai Zhu, Jun Sun, Jingyi Wang, Zhenbang Chen, Peng Cheng
2026 J jnl
STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling.
CoRR
Kun Wang, Meng Chen, Junhao Wang, Yuli Wu, Li Lu, Chong Zhang, Peng Cheng, Jiaheng Zhang, Kui Ren
2025 J jnl
ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models.
CoRR
Jianxin Yan, Wangze Ni, Lei Chen, Xuemin Lin, Peng Cheng, Zhan Qin, Kui Ren
2025 J jnl
ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models.
Proc. VLDB Endow.
Jianxin Yan, Wangze Ni, Lei Chen, Xuemin Lin, Peng Cheng, Zhan Qin, Kui Ren
2025 J jnl
Imperceptible but Forgeable: Practical Invisible Watermark Forgery via Diffusion Models.
CoRR
Ziping Dong, Chao Shuai, Zhongjie Ba, Peng Cheng, Zhan Qin, Qinglong Wang, Kui Ren
2025 J jnl
Phoneme-Based Proactive Anti-Eavesdropping With Controlled Recording Privilege.
IEEE Trans. Dependable Secur. Comput.
Peng Huang, Yao Wei, Peng Cheng, Zhongjie Ba, Li Lu, Feng Lin, Yang Wang, Kui Ren
2025 J jnl
Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation.
CoRR
Zhongjie Ba, Yitao Zhang, Peng Cheng, Bin Gong, Xinyu Zhang, Qinglong Wang, Kui Ren
2025 A conf
SecHeadset: A Practical Privacy Protection System for Real-time Voice Communication.
MobiSys
Peng Huang, Kun Pan, Qinglong Wang, Peng Cheng, Li Lu, Zhongjie Ba, Kui Ren
2024 A* conf
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features.
SP
Peng Cheng, Yuwei Wang, Peng Huang, Zhongjie Ba, Xiaodong Lin, Feng Lin, Li Lu, Kui Ren
2024 J jnl
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features.
CoRR
Peng Cheng, Yuwei Wang, Peng Huang, Zhongjie Ba, Xiaodong Lin, Feng Lin, Li Lu, Kui Ren
2024 J jnl
Indelible "Footprints" of Inaudible Command Injection.
IEEE Trans. Inf. Forensics Secur.
Zhongjie Ba, Bin Gong, Yuwei Wang, Yuxuan Liu, Peng Cheng, Feng Lin, Li Lu, Kui Ren
2024 J jnl
Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege.
CoRR
Peng Huang, Yao Wei, Peng Cheng, Zhongjie Ba, Li Lu, Feng Lin, Yang Wang, Kui Ren
2024 A* conf
SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution.
CCS
Zhongjie Ba, Jieming Zhong, Jiachen Lei, Peng Cheng, Qinglong Wang, Zhan Qin, Zhibo Wang, Kui Ren
2024 J jnl
UniAP: Protecting Speech Privacy With Non-Targeted Universal Adversarial Perturbations.
IEEE Trans. Dependable Secur. Comput.
Peng Cheng, Yuexin Wu, Yuan Hong, Zhongjie Ba, Feng Lin, Li Lu, Kui Ren
2023 A* conf
InfoMasker: Preventing Eavesdropping Using Phoneme-Based Noise.
NDSS
Peng Huang, Yao Wei, Peng Cheng, Zhongjie Ba, Li Lu, Feng Lin, Fan Zhang, Kui Ren
2023 J jnl
Masked Diffusion Models are Fast Learners.
CoRR
Jiachen Lei, Peng Cheng, Zhongjie Ba, Kui Ren
2023 J jnl
SurrogatePrompt: Bypassing the Safety Filter of Text-To-Image Models via Substitution.
CoRR
Zhongjie Ba, Jieming Zhong, Jiachen Lei, Peng Cheng, Qinglong Wang, Zhan Qin, Zhibo Wang, Kui Ren
2023 A* conf
Transferring Audio Deepfake Detection Capability across Languages.
WWW
Zhongjie Ba, Qing Wen, Peng Cheng, Yuwei Wang, Feng Lin, Li Lu, Zhenguang Liu
2022 J jnl
Personal Voice Assistant Security and Privacy - A Survey.
Proc. IEEE
Peng Cheng, Utz Roedig
2021 — conf
Adversarial Command Detection Using Parallel Speech Recognition Systems.
CyberICPS/SECPRE/ADIoT/SPOSE/CPS4CIP/CDT&SECOMANE@ESORICS
Peng Cheng, M. S. Arun Sankar, Ibrahim Ethem Bagci, Utz Roedig
2020 — —
Acoustic-channel attack and defence methods for personal voice assistants.
Peng Cheng
2020 J jnl
SonarSnoop: active acoustic side-channel attacks.
Int. J. Inf. Sec.
Peng Cheng, Ibrahim Ethem Bagci, Utz Roedig, Jeff Yan
2019 — conf
Smart Speaker Privacy Control - Acoustic Tagging for Personal Voice Assistants.
IEEE Symposium on Security and Privacy Workshops
Peng Cheng, Ibrahim Ethem Bagci, Jeff Yan, Utz Roedig
2018 J jnl
SonarSnoop: Active Acoustic Side-Channel Attacks.
CoRR
Peng Cheng, Ibrahim Ethem Bagci, Utz Roedig, Jeff Yan
2018 — conf
Towards Reactive Acoustic Jamming for Personal Voice Assistants.
MPS@CCS
Peng Cheng, Ibrahim Ethem Bagci, Jeff Yan, Utz Roedig