Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
Wenjie Fu, Chen Gao, Tao Jiang, Yong Li, Guanghua Liu, Huandong Wang
Topics & Concepts
Computer scienceCalibrationArtificial intelligenceInferenceData miningNatural language processingMachine learningFeature (linguistics)Key (lock)Language modelAlgorithmAdversarial Robustness in Machine LearningTopic ModelingExplainable Artificial Intelligence (XAI)