research
∙
09/13/2023
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems
Speaker Verification (SV) is widely deployed in mobile systems to authen...
share
research
∙
09/13/2023
PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection
In this paper, we propose PhantomSound, a query-efficient black-box atta...
research
∙
07/14/2023
Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots
Recent advances in natural language processing and machine learning have...
research
∙
05/09/2023
VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation
Deep learning based voice synthesis technology generates artificial huma...
research
∙
02/07/2023
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where ad...
research
∙
07/12/2022
NEC: Speaker Selective Cancellation via Neural Enhanced Ultrasound Shadowing
In this paper, we propose NEC (Neural Enhanced Cancellation), a defense ...
research
∙
05/28/2022
SuperVoice: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speech
Voice-activated systems are integrated into a variety of desktop, mobile...
research
∙
02/05/2022
GhostTalk: Interactive Attack on Smartphone Voice System Through Power Line
Inaudible voice command injection is one of the most threatening attacks...
research
∙
07/17/2021
Rectifying Administrated ERC20 Tokens
The developers of Ethereum smart contracts often implement administratin...
research
∙
11/05/2018
DSIC: Deep Learning based Self-Interference Cancellation for In-Band Full Duplex Wireless
In-band full duplex wireless is of utmost interest to future wireless co...
research
∙
08/14/2018