Seungmin Kim

M.S. in Software, Soongsil University

Expected Feb. 2027 · GPA 4.5 / 4.5

Research focus: AI safety, adversarial robustness, speech AI security.

B.S. in Software, Soongsil University

GPA 3.0 / 4.5

Undergraduate Research Intern

AI Safety Center, Soongsil University

Speech AI security research — deepfake-voice detection and proactive voice protection against AI-based voice cloning.

NaVo: Natural Voice Protection against Voice Cloning Attacks via Generative Universal Adversarial Audio

Interspeech 2026 · Accepted

Seoyoung Park*, Seungmin Kim*, Sohee Park, Dain Kim, et al.

*These authors contributed equally and are listed in alphabetical order.

RoCo: Robust Code for Fast and Effective Proactive Defense against Voice Cloning Attack

ICASSP 2026 · Oral

Seungmin Kim*, Dain Kim*, Sohee Park, Daeseon Choi

*These authors contributed equally to this work.

Session Replication Attack Through QR Code Sniffing in Passkey CTAP Registration

IFIP SEC 2024

Donghyun Kim, Seungmin Kim, Gwonsang Ryu, Daeseon Choi

Face Verifiable Anonymization in Video Surveillance

WISA 2023

Sungjune Park, Hyunsik Na, Seungmin Kim, Daeseon Choi

Real-time Deepfake Disruption via Adversarial Noise Injection

Personal Information Protection Commission (PIPC)

Proactive defense against voice-cloning attacks. Led proposal preparation.

Countermeasure Technologies for Generative-AI Security Threats

IITP

Deepfake defense technologies. Participated in proposal preparation.

Robust AI & Distributed Attack Detection for Edge AI Security

IITP

DeepVoice detection and voice-deepfake security for smart speakers; built a prototype edge-AI attack-simulation system.