Sequence Squeezing: A Defense Method against Adversarial Examples for API Call-Based RNN Variants

Keyphrases

• Adversarial Attack 28%
• Adversarial Defense 14%
• Adversarial Example Generation 14%
• Adversarial Examples 100%
• Anti-attack 14%
• API Calls 100%
• Attack Strategy 14%
• Computer Vision 14%
• Convolutional Neural Network 28%
• Deep Learning Model 14%
• Defense Method 100%
• Generation Method 14%
• LSTM Classifier 14%
• Network Defense 14%
• Neural Network Classifier 14%
• Recurrent Neural Network 100%
• Sequence-to-sequence Model 14%
• State-of-the-art Performance 14%

Computer Science

• Adversarial Example 100%
• Adversarial Machine Learning 50%
• Art Performance 25%
• Computer Vision 25%
• Convolutional Neural Network 50%
• Deep Learning Model 25%
• Inspired Method 25%
• Long Short-Term Memory Network 25%
• Network Defense 25%
• Recurrent Neural Network 100%