Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs

Ruixuan Liu, David Evans 0001, Li Xiong 0001. Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs. In IEEE Symposium on Security and Privacy, SP 2026, San Francisco, CA, USA, May 18-21, 2026. pages 1654-1672, IEEE, 2026. [doi]

Authors

Ruixuan Liu

This author has not been identified. Look up 'Ruixuan Liu' in Google

David Evans 0001

This author has not been identified. Look up 'David Evans 0001' in Google

Li Xiong 0001

This author has not been identified. Look up 'Li Xiong 0001' in Google