10 papers
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
Kichang Lee, Yujin Shin, Jonghyuk Yun +3
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. Howeve…
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fall…
Spatial Discretization for Fine-Grain Zone Checks with STARKs
Sungmin Lee, Kichang Lee, Gyeongmin Han +1
Many location-based services rely on a point-in-polygon test (PiP), checking whether a point or a trajectory lies inside a geographic zone. Since geometric operations are expensive…
Now or Never: Continuous Surveillance AIoT System for Ephemeral Events in Intermittent Sensor Networks
Joonhee Lee, Kichang Lee, Jeonggil Ko
Wilderness monitoring tasks, such as poaching surveillance and forest fire detection, require pervasive and high-accuracy sensing. While AIoT offers a promising path, covering vast…
Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
Kichang Lee, Jaeho Jin, JaeYeon Park +2
Federated learning enables decentralized model training without sharing raw data, preserving data privacy. However, its vulnerability towards critical security threats, such as gra…
Verifiable Dropout: Turning Randomness into a Verifiable Claim
Kichang Lee, Sungmin Lee, Jaeho Jin +1
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address t…