Leo Marchyok

According to our database, Leo Marchyok authored at least 3 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Discovering Universal Activation Directions for PII Leakage in Language Models.

Leo Marchyok, Zachary Coalson, Sungho Keum, Sooel Son, Sanghyun Hong

CoRR, February, 2026

2025

Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts.

Seongho Keum, Dongwon Shin, Leo Marchyok, Sanghyun Hong, Sooel Son

Proceedings of the 34th USENIX Security Symposium, 2025

2024

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.

Yuxin Wen, Leo Marchyok, Sanghyun Hong, Jonas Geiping, Tom Goldstein, Nicholas Carlini

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024