Explanation leaks: Explanation-guided model extraction attacks
Anli Yan, Teng Huang, Lishan Ke, Xiaozhang Liu, Qi Chen, Changyu Dong
Topics & Concepts
Computer scienceTransparency (behavior)AdversaryExploitKey (lock)FidelityAttack modelComputer securityArtificial intelligenceTelecommunicationsAdversarial Robustness in Machine LearningExplainable Artificial Intelligence (XAI)Anomaly Detection Techniques and Applications