Institute of Science Tokyo · School of Computing

Research keywordsmachine learning security・data reconstruction attacks・model stealing・LLM guardrails・data valuation attacks・capture-the-flag benchmarking

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?2025 · NDSS 2025年2月
• Peering Behind the Shield: Guardrail Identification in Large Language Models.2025 · CoRR abs/2502.01241 2025年2月
• SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark2025 · 34rd USENIX Security Symposium 2025年8月
• Quantifying Privacy Risks of Prompts in Visual Prompt Learning.2024 · 33rd USENIX Security Symposium 2024年8月

• Official profile