Android Malware Detection
Detection of Android Malware using Machine Learning
@kaggle.subhajournal_android_malware_detection
About this Dataset
Android Malware Detection
Android Malware detection using machine learning is an approach to detecting and classifying malicious applications for Android devices. One of the precise way to identify the suspiciousness of applications is by monitoring the network on which the android device is connected. Machine learning is a subset of artificial intelligence which focuses on the development of computer programs that can access data and use it to learn for themselves. This technology can be used to build models that evaluate incoming data in order to make predictions and detect anomalies. This can be applied to the detection of malicious Android applications, by building a model that looks for patterns associated with malware behaviour. The model could use a variety of features, such as permissions requested, API calls made, network activity, etc. Once trained the model can then be deployed to classify any new application as malicious or non-malicious.
Tables
Android Malware
@kaggle.subhajournal_android_malware_detection.android_malware
- 57.22 MB
- 355630 rows
- 86 columns
Loading...
CREATE TABLE android_malware (
"unnamed_0" BIGINT,
"flow_id" VARCHAR,
"n__source_ip" VARCHAR,
"n__source_port" BIGINT,
"n__destination_ip" VARCHAR,
"n__destination_port" DOUBLE,
"n__protocol" DOUBLE,
"n__timestamp" VARCHAR,
"n__flow_duration" BIGINT,
"n__total_fwd_packets" BIGINT,
"n__total_backward_packets" BIGINT,
"total_length_of_fwd_packets" DOUBLE,
"n__total_length_of_bwd_packets" DOUBLE,
"n__fwd_packet_length_max" DOUBLE,
"n__fwd_packet_length_min" DOUBLE,
"n__fwd_packet_length_mean" DOUBLE,
"n__fwd_packet_length_std" DOUBLE,
"bwd_packet_length_max" DOUBLE,
"n__bwd_packet_length_min" DOUBLE,
"n__bwd_packet_length_mean" DOUBLE,
"n__bwd_packet_length_std" DOUBLE,
"flow_bytes_s" DOUBLE,
"n__flow_packets_s" DOUBLE,
"n__flow_iat_mean" DOUBLE,
"n__flow_iat_std" DOUBLE,
"n__flow_iat_max" DOUBLE,
"n__flow_iat_min" DOUBLE,
"fwd_iat_total" DOUBLE,
"n__fwd_iat_mean" DOUBLE,
"n__fwd_iat_std" DOUBLE,
"n__fwd_iat_max" DOUBLE,
"n__fwd_iat_min" DOUBLE,
"bwd_iat_total" DOUBLE,
"n__bwd_iat_mean" DOUBLE,
"n__bwd_iat_std" DOUBLE,
"n__bwd_iat_max" DOUBLE,
"n__bwd_iat_min" DOUBLE,
"fwd_psh_flags" DOUBLE,
"n__bwd_psh_flags" DOUBLE,
"n__fwd_urg_flags" BIGINT,
"n__bwd_urg_flags" BIGINT,
"n__fwd_header_length" BIGINT,
"n__bwd_header_length" BIGINT,
"fwd_packets_s" DOUBLE,
"n__bwd_packets_s" DOUBLE,
"n__min_packet_length" DOUBLE,
"n__max_packet_length" DOUBLE,
"n__packet_length_mean" DOUBLE,
"n__packet_length_std" DOUBLE,
"n__packet_length_variance" DOUBLE,
"fin_flag_count" DOUBLE,
"n__syn_flag_count" DOUBLE,
"n__rst_flag_count" DOUBLE,
"n__psh_flag_count" DOUBLE,
"n__ack_flag_count" DOUBLE,
"n__urg_flag_count" DOUBLE,
"n__cwe_flag_count" VARCHAR,
"n__ece_flag_count" DOUBLE,
"n__down_up_ratio" VARCHAR,
"n__average_packet_size" DOUBLE,
"n__avg_fwd_segment_size" DOUBLE,
"n__avg_bwd_segment_size" DOUBLE,
"n__fwd_header_length_1" DOUBLE,
"fwd_avg_bytes_bulk" VARCHAR,
"n__fwd_avg_packets_bulk" DOUBLE,
"n__fwd_avg_bulk_rate" DOUBLE,
"n__bwd_avg_bytes_bulk" DOUBLE,
"n__bwd_avg_packets_bulk" DOUBLE,
"bwd_avg_bulk_rate" DOUBLE,
"subflow_fwd_packets" DOUBLE,
"n__subflow_fwd_bytes" DOUBLE,
"n__subflow_bwd_packets" DOUBLE,
"n__subflow_bwd_bytes" DOUBLE,
"init_win_bytes_forward" DOUBLE,
"n__init_win_bytes_backward" DOUBLE,
"n__act_data_pkt_fwd" DOUBLE,
"n__min_seg_size_forward" DOUBLE,
"active_mean" DOUBLE,
"n__active_std" DOUBLE,
"n__active_max" DOUBLE,
"n__active_min" DOUBLE,
"idle_mean" DOUBLE,
"n__idle_std" DOUBLE,
"n__idle_max" DOUBLE,
"n__idle_min" DOUBLE,
"label" VARCHAR
);