| machine learning : 機器學習 deep learning : 深度學習 image processing : 圖像處理 natural language processing : 自然語言處理 algorithms : 算法 training data set : 訓練數據集 facial detection : 面部識別 malware detection : 惡意程序檢測 adversarial sample : 對抗樣本 countermeasuring techniques : 防御技術 Indiscriminate Attack:非針對性攻擊 Adversary’s goal:敵手目標 Adversary’s knowledge :敵手知識 Adversary’s capability:敵手能力 Attack strategy:攻擊策略 Gradient Ascent Strategy:梯度下降策略 Generative Model:生成模型 Discriminative model:判別模型 The Direct Gradient:直接梯度法 Accuracy:准確率 Loss:損失值 White-Box Attack:白盒攻擊 Blank-Box Attack:黑盒攻擊 Reconstruction Attack:重建攻擊 Proactive Defense:主動防御 Reactive Defense:被動防御 Reject On Negative Impact:拒絕消極影響 Stackelberg Games:斯塔克爾伯格博弈 Defensive Distillation:防御精餾 Differential Privacy:差分隱私 Homomorphic Encryption:同態加密 Pattern Recognition:模式識別 RNN, Recurrent Neural Networks:循環神經網絡 FNNs(Feed-forward Neural Networks):前向反饋神經網絡 Convolutional layer:卷積層 Rectified Linear Units layer,ReLU layer:線性整流層 Pooling layer :池化層 Fully-Connected layer:全連接層 |
Face Recognition System :面部識別系統 (FRS) Adversarial Classification : 敵手分類 Adversarial Learning :對抗學習 try-and-error:試錯 Causative Attack :誘發型攻擊 Security Violation :安全損害 Integrity Attack :完整性攻擊 Availability Attack:可用性攻擊 Privacy Violation Attack :隱私竊取攻擊 Specificity of an Attack :攻擊的專一性 Obfuscation Attacks:迷惑攻擊 Counterintuitive:反直覺 Poisoning Attack:投毒攻擊 Centroid:中心值 Bridge:橋 Spoofing Attack :欺騙攻擊 Avoiding Attack:逃避攻擊 Impersonate Attack:模仿攻擊 The Least Likely Class:最小相似類 Inversion Attack:逆向攻擊 Confidence Values:置信值 Equation-Solving Attacks:等式求解攻擊 Model Extraction Attacks:模型提取攻擊 Arms Race:攻防技術競賽 Non-stationary:不平穩 Data Sanitization:數據清洗 Randomized Prediction Games:隨機預測博弈 Deep Contractive Networks:深度收縮網絡 Crowdsourcing:眾包 Randomized Response:隨機響應 Logistic Regression:邏輯回歸 regression analysis:回歸分析 |
