most citedSCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

19 citations · 51 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CR2023

MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems

Hanqing Guo, Xun Chen, Junfeng Guo +2

Speaker Verification (SV) is widely deployed in mobile systems to authenticate legitimate users by using their voice traits. In this work, we propose a backdoor attack MASTERKEY, t…

cs.CR20231 cited

PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection

Hanqing Guo, Guangjing Wang, Yuanda Wang +3

In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitu…

cs.CR202317 cited

Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots

Bocheng Chen, Guangjing Wang, Hanqing Guo +2

Recent advances in natural language processing and machine learning have led to the development of chatbot models, such as ChatGPT, that can engage in conversational dialogue with…

cs.SD202314 cited

VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation

Yuanda Wang, Hanqing Guo, Guangjing Wang +2

Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inj…

cs.CR202319 cited

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Junfeng Guo, Yiming Li, Xun Chen +3

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation.…

cs.SD2022

NEC: Speaker Selective Cancellation via Neural Enhanced Ultrasound Shadowing

Hanqing Guo, Chenning Li, Lingkun Li +3

In this paper, we propose NEC (Neural Enhanced Cancellation), a defense mechanism, which prevents unauthorized microphones from capturing a target speaker's voice. Compared with th…