Datasets:

mmalensek
/

flowexplain-dataset

Error code:   DatasetGenerationCastError
Exception:    DatasetGenerationCastError
Message:      An error occurred while generating the dataset

All the data files must have the same columns, but at some point there are 1 new columns ({'messages'}) and 10 missing columns ({'previous_flows', 'xgb_label', 'user', 'source_file', 'next_flows', 'actual_label', 'probabilities', 'current_flow', 'label', 'assistant'}).

This happened while the json dataset builder was generating data using

hf://datasets/mmalensek/flowexplain-dataset/training_dataset.jsonl (at revision dd6d08d25702471949ffa834a26eeac202e733b7), ['hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.json', 'hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.jsonl'], ['hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.json', 'hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.jsonl']

Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1848, in _prepare_split_single
                  writer.write_table(table)
                  ~~~~~~~~~~~~~~~~~~^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/arrow_writer.py", line 765, in write_table
                  self._write_table(pa_table, writer_batch_size=writer_batch_size)
                  ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/arrow_writer.py", line 773, in _write_table
                  pa_table = table_cast(pa_table, self._schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2378, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2306, in cast_table_to_schema
                  raise CastError(
                  ...<3 lines>...
                  )
              datasets.table.CastError: Couldn't cast
              messages: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              to
              {'source_file': Value('string'), 'label': Value('string'), 'actual_label': Value('string'), 'user': Value('string'), 'assistant': Value('string'), 'current_flow': {' Source Port': Value('int64'), ' Destination Port': Value('int64'), ' Protocol': Value('int64'), ' Flow Duration': Value('int64'), ' Total Fwd Packets': Value('int64'), ' Total Backward Packets': Value('int64'), 'Total Length of Fwd Packets': Value('float64'), ' Total Length of Bwd Packets': Value('float64'), ' Fwd Packet Length Max': Value('float64'), ' Fwd Packet Length Min': Value('float64'), ' Fwd Packet Length Mean': Value('float64'), ' Fwd Packet Length Std': Value('float64'), 'Bwd Packet Length Max': Value('float64'), ' Bwd Packet Length Min': Value('float64'), ' Bwd Packet Length Mean': Value('float64'), ' Bwd Packet Length Std': Value('float64'), 'Flow Bytes/s': Value('float64'), ' Flow Packets/s': Value('float64'), ' Flow IAT Mean': Value('float64'), ' Flow IAT Std': Value('float64'), ' Flow IAT Max': Value('float64'), ' Flow IAT Min': Value('float64'), 'Fwd IAT Total': Value('float64'), ' Fwd IAT Mean': Value('float64'), ' Fwd IAT Std': Value('float64'), ' Fwd IAT Max': Value('float64'), ' Fwd IAT Min': Value('float64'), 'Bwd IAT Total': Value('float64'), ' Bwd IAT Mean': Value('float64'), ' Bwd IAT Std': Value('float64'), ' Bwd IAT Max': Value('float64'), ' Bwd IAT Min': Value('float64'), 'Fwd PSH Flags': Value('int64'), ' Bwd PSH Flags': Value('int64'), ' Fwd URG Flags': Value('int64'), ' Bwd URG Flag
              ...
              ze': Value('float64'), ' Avg Bwd Segment Size': Value('float64'), ' Fwd Header Length.1': Value('int64'), 'Fwd Avg Bytes/Bulk': Value('int64'), ' Fwd Avg Packets/Bulk': Value('int64'), ' Fwd Avg Bulk Rate': Value('int64'), ' Bwd Avg Bytes/Bulk': Value('int64'), ' Bwd Avg Packets/Bulk': Value('int64'), 'Bwd Avg Bulk Rate': Value('int64'), 'Subflow Fwd Packets': Value('int64'), ' Subflow Fwd Bytes': Value('int64'), ' Subflow Bwd Packets': Value('int64'), ' Subflow Bwd Bytes': Value('int64'), 'Init_Win_bytes_forward': Value('int64'), ' Init_Win_bytes_backward': Value('int64'), ' act_data_pkt_fwd': Value('int64'), ' min_seg_size_forward': Value('int64'), 'Active Mean': Value('float64'), ' Active Std': Value('float64'), ' Active Max': Value('float64'), ' Active Min': Value('float64'), 'Idle Mean': Value('float64'), ' Idle Std': Value('float64'), ' Idle Max': Value('float64'), ' Idle Min': Value('float64'), ' Label': Value('string')}), 'xgb_label': Value('string'), 'probabilities': {'BENIGN': Value('float64'), 'Bot': Value('float64'), 'DDoS': Value('float64'), 'DoS GoldenEye': Value('float64'), 'DoS Hulk': Value('float64'), 'DoS Slowhttptest': Value('float64'), 'DoS slowloris': Value('float64'), 'FTP-Patator': Value('float64'), 'Heartbleed': Value('float64'), 'Infiltration': Value('float64'), 'PortScan': Value('float64'), 'SSH-Patator': Value('float64'), 'Web Attack  Brute Force': Value('float64'), 'Web Attack  Sql Injection': Value('float64'), 'Web Attack  XSS': Value('float64')}}
              because column names don't match
              
              During handling of the above exception, another exception occurred:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1369, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ~~~~~~~~~~~~~~~~~~~~~~~~~^
                      builder, max_dataset_size_bytes=max_dataset_size_bytes
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  )
                  ^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 948, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                  ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1694, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ~~~~~~~~~~~~~~~~~~~~~~~~~~^
                      gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  ):
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1850, in _prepare_split_single
                  raise DatasetGenerationCastError.from_cast_error(
                  ...<4 lines>...
                  )
              datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
              
              All the data files must have the same columns, but at some point there are 1 new columns ({'messages'}) and 10 missing columns ({'previous_flows', 'xgb_label', 'user', 'source_file', 'next_flows', 'actual_label', 'probabilities', 'current_flow', 'label', 'assistant'}).
              
              This happened while the json dataset builder was generating data using
              
              hf://datasets/mmalensek/flowexplain-dataset/training_dataset.jsonl (at revision dd6d08d25702471949ffa834a26eeac202e733b7), ['hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.json', 'hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.jsonl'], ['hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.json', 'hf://datasets/mmalensek/flowexplain-dataset@dd6d08d25702471949ffa834a26eeac202e733b7/training_dataset.jsonl']
              
              Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

source_file string	label string	actual_label string	user string	assistant string	current_flow dict	previous_flows list	next_flows list	xgb_label string	probabilities dict
json_log/3_evaluation_results/6_score_winner/winner_20260722_172325.json	BENIGN	BENIGN	Analyze this network traffic. Provide your response EXACTLY in the following format: LABEL: [attack label] REASONING: [analysis] SOLUTION: [recommended mitigations] Actual label: BENIGN XGBoost prediction: BENIGN Current flow: { " Source Port": 19556, " Destination Port": 53, " Protocol": 17, " Flow Durat...	LABEL: BENIGN REASONING: The current flow is UDP (protocol 17) from a high ephemeral source port to destination port 53, with 2 forward packets and 2 backward packets and small payload sizes (36B request, ~130B response). This is consistent with a normal DNS query/response exchange. The surrounding flows show multiple...	{ " Source Port": 19556, " Destination Port": 53, " Protocol": 17, " Flow Duration": 987286, " Total Fwd Packets": 2, " Total Backward Packets": 2, "Total Length of Fwd Packets": 72, " Total Length of Bwd Packets": 260, " Fwd Packet Length Max": 36, " Fwd Packet Length Min": 36, " Fwd Packet Lengt...	[ { " Source Port": 35946, " Destination Port": 53, " Protocol": 17, " Flow Duration": 240, " Total Fwd Packets": 2, " Total Backward Packets": 2, "Total Length of Fwd Packets": 60, " Total Length of Bwd Packets": 264, " Fwd Packet Length Max": 30, " Fwd Packet Length Min": 30,...	[ { " Source Port": 42294, " Destination Port": 53, " Protocol": 17, " Flow Duration": 288, " Total Fwd Packets": 2, " Total Backward Packets": 2, "Total Length of Fwd Packets": 72, " Total Length of Bwd Packets": 460, " Fwd Packet Length Max": 36, " Fwd Packet Length Min": 36,...	BENIGN	{ "BENIGN": 1, "Bot": 0, "DDoS": 0, "DoS GoldenEye": 0, "DoS Hulk": 0, "DoS Slowhttptest": 0, "DoS slowloris": 0, "FTP-Patator": 0, "Heartbleed": 0, "Infiltration": 0, "PortScan": 0, "SSH-Patator": 0, "Web Attack Brute Force": 0, "Web Attack Sql Injection": 0, "Web Attack XSS": 0 }
json_log/3_evaluation_results/6_score_winner/winner_20260722_172817.json	BENIGN	BENIGN	Analyze this network traffic. Provide your response EXACTLY in the following format: LABEL: [attack label] REASONING: [analysis] SOLUTION: [recommended mitigations] Actual label: BENIGN XGBoost prediction: BENIGN Current flow: { " Source Port": 43601, " Destination Port": 53, " Protocol": 17, " Flow Durat...	LABEL: BENIGN REASONING: The current flow is UDP (protocol 17) from a high ephemeral source port (43601) to destination port 53, consistent with a DNS query/response exchange. It contains 2 forward and 2 backward packets with small, fixed packet sizes (71B outbound, 121B inbound) and a very short flow duration (163), ...	{ " Source Port": 43601, " Destination Port": 53, " Protocol": 17, " Flow Duration": 163, " Total Fwd Packets": 2, " Total Backward Packets": 2, "Total Length of Fwd Packets": 142, " Total Length of Bwd Packets": 242, " Fwd Packet Length Max": 71, " Fwd Packet Length Min": 71, " Fwd Packet Length ...	[ { " Source Port": 443, " Destination Port": 50205, " Protocol": 6, " Flow Duration": 23, " Total Fwd Packets": 1, " Total Backward Packets": 1, "Total Length of Fwd Packets": 6, " Total Length of Bwd Packets": 6, " Fwd Packet Length Max": 6, " Fwd Packet Length Min": 6, "...	[ { " Source Port": 443, " Destination Port": 56441, " Protocol": 6, " Flow Duration": 50, " Total Fwd Packets": 1, " Total Backward Packets": 1, "Total Length of Fwd Packets": 0, " Total Length of Bwd Packets": 0, " Fwd Packet Length Max": 0, " Fwd Packet Length Min": 0, "...	BENIGN	{ "BENIGN": 1, "Bot": 0, "DDoS": 0, "DoS GoldenEye": 0, "DoS Hulk": 0, "DoS Slowhttptest": 0, "DoS slowloris": 0, "FTP-Patator": 0, "Heartbleed": 0, "Infiltration": 0, "PortScan": 0, "SSH-Patator": 0, "Web Attack Brute Force": 0, "Web Attack Sql Injection": 0, "Web Attack XSS": 0 }
json_log/3_evaluation_results/6_score_winner/winner_20260722_173629.json	BENIGN	BENIGN	Analyze this network traffic. Provide your response EXACTLY in the following format: LABEL: [attack label] REASONING: [analysis] SOLUTION: [recommended mitigations] Actual label: BENIGN XGBoost prediction: BENIGN Current flow: { " Source Port": 60654, " Destination Port": 53, " Protocol": 17, " Flow Durat...	LABEL: BENIGN REASONING: The current flow is a single UDP exchange from an ephemeral source port (60654) to destination port 53 (DNS): 1 forward packet (64B) and 1 backward packet (157B) over ~1 ms. This “1 query / 1 response” pattern, small payload sizes, and lack of TCP flags are consistent with a normal DNS lookup....	{ " Source Port": 60654, " Destination Port": 53, " Protocol": 17, " Flow Duration": 1054, " Total Fwd Packets": 1, " Total Backward Packets": 1, "Total Length of Fwd Packets": 64, " Total Length of Bwd Packets": 157, " Fwd Packet Length Max": 64, " Fwd Packet Length Min": 64, " Fwd Packet Length ...	[ { " Source Port": 123, " Destination Port": 123, " Protocol": 17, " Flow Duration": 94114, " Total Fwd Packets": 1, " Total Backward Packets": 1, "Total Length of Fwd Packets": 48, " Total Length of Bwd Packets": 48, " Fwd Packet Length Max": 48, " Fwd Packet Length Min": 48,...	[ { " Source Port": 62019, " Destination Port": 53, " Protocol": 17, " Flow Duration": 50543, " Total Fwd Packets": 1, " Total Backward Packets": 1, "Total Length of Fwd Packets": 44, " Total Length of Bwd Packets": 60, " Fwd Packet Length Max": 44, " Fwd Packet Length Min": 44...	BENIGN	{ "BENIGN": 1, "Bot": 0, "DDoS": 0, "DoS GoldenEye": 0, "DoS Hulk": 0, "DoS Slowhttptest": 0, "DoS slowloris": 0, "FTP-Patator": 0, "Heartbleed": 0, "Infiltration": 0, "PortScan": 0, "SSH-Patator": 0, "Web Attack Brute Force": 0, "Web Attack Sql Injection": 0, "Web Attack XSS": 0 }
json_log/3_evaluation_results/6_score_winner/winner_20260722_174449.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe current flow is UDP (protocol 17) from a high ephemeral source po(...TRUNCATED)	{" Source Port":58460," Destination Port":53," Protocol":17," Flow Duration":30925," Total Fwd Packe(...TRUNCATED)	[{" Source Port":11849," Destination Port":53," Protocol":17," Flow Duration":81," Total Fwd Packets(...TRUNCATED)	[{" Source Port":54889," Destination Port":53," Protocol":17," Flow Duration":31113," Total Fwd Pack(...TRUNCATED)	BENIGN	{"BENIGN":1.0,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS sl(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_175104.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe current flow is a long-lived TCP connection from a high ephemeral(...TRUNCATED)	{" Source Port":40353," Destination Port":443," Protocol":6," Flow Duration":116052869," Total Fwd P(...TRUNCATED)	[{" Source Port":40704," Destination Port":443," Protocol":6," Flow Duration":115118633," Total Fwd (...TRUNCATED)	[{" Source Port":37949," Destination Port":443," Protocol":6," Flow Duration":116088944," Total Fwd (...TRUNCATED)	BENIGN	{"BENIGN":0.9999,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_175919.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe flow is TCP (protocol 6) with source port 80 to a high ephemeral (...TRUNCATED)	{" Source Port":80," Destination Port":38126," Protocol":6," Flow Duration":7598272," Total Fwd Pack(...TRUNCATED)	[{" Source Port":80," Destination Port":38129," Protocol":6," Flow Duration":7603330," Total Fwd Pac(...TRUNCATED)	[{" Source Port":80," Destination Port":59870," Protocol":6," Flow Duration":5398374," Total Fwd Pac(...TRUNCATED)	BENIGN	{"BENIGN":0.9999,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_180508.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe current flow is UDP (protocol 17) from a high ephemeral source po(...TRUNCATED)	{" Source Port":44834," Destination Port":53," Protocol":17," Flow Duration":294," Total Fwd Packets(...TRUNCATED)	[{" Source Port":58986," Destination Port":53," Protocol":17," Flow Duration":31072," Total Fwd Pack(...TRUNCATED)	[{" Source Port":51153," Destination Port":53," Protocol":17," Flow Duration":212," Total Fwd Packet(...TRUNCATED)	BENIGN	{"BENIGN":1.0,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS sl(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_181146.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe flow is a very short TCP exchange involving port 443 (HTTPS) to a(...TRUNCATED)	{" Source Port":443," Destination Port":49646," Protocol":6," Flow Duration":34," Total Fwd Packets"(...TRUNCATED)	[{" Source Port":59467," Destination Port":53," Protocol":17," Flow Duration":30814," Total Fwd Pack(...TRUNCATED)	[{" Source Port":39947," Destination Port":53," Protocol":17," Flow Duration":119," Total Fwd Packet(...TRUNCATED)	BENIGN	{"BENIGN":0.9998,"Bot":0.0001,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_181710.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe flow is a TCP connection from a high ephemeral source port (54245(...TRUNCATED)	{" Source Port":54245," Destination Port":443," Protocol":6," Flow Duration":5926827," Total Fwd Pac(...TRUNCATED)	[{" Source Port":54247," Destination Port":443," Protocol":6," Flow Duration":5817653," Total Fwd Pa(...TRUNCATED)	[{" Source Port":54236," Destination Port":443," Protocol":6," Flow Duration":115350422," Total Fwd (...TRUNCATED)	BENIGN	{"BENIGN":0.9999,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS(...TRUNCATED)
json_log/3_evaluation_results/6_score_winner/winner_20260722_182311.json	BENIGN	BENIGN	"Analyze this network traffic.\n\nProvide your response EXACTLY in the following format:\n\nLABEL:\n(...TRUNCATED)	"LABEL:\nBENIGN\n\nREASONING:\nThe current flow is UDP (Protocol 17) from a high ephemeral source po(...TRUNCATED)	{" Source Port":61041," Destination Port":53," Protocol":17," Flow Duration":19222," Total Fwd Packe(...TRUNCATED)	[{" Source Port":60086," Destination Port":53," Protocol":17," Flow Duration":23839," Total Fwd Pack(...TRUNCATED)	[{" Source Port":2266," Destination Port":53," Protocol":17," Flow Duration":247," Total Fwd Packets(...TRUNCATED)	BENIGN	{"BENIGN":1.0,"Bot":0.0,"DDoS":0.0,"DoS GoldenEye":0.0,"DoS Hulk":0.0,"DoS Slowhttptest":0.0,"DoS sl(...TRUNCATED)

End of preview.

FlowExplain Training Dataset — Network Intrusion Explanations

711 examples pairing a classified network flow (from CICIDS2017) with a winning, natural-language explanation (label, reasoning, mitigation recommendation). Collected as part of FlowExplain, the system built for the diploma thesis "Explainable Network Intrusion Detection with Large Language Models" (Faculty of Computer and Information Science, University of Ljubljana).

Code: mmalensek/SNIC_Network_Security
Companion model (LoRA fine-tuned on this data): mmalensek/flowexplain-deepseek-r1-8b-lora

How the winning explanation was chosen

For each flow, three candidate explanations were generated in parallel:

a local model (deepseek-r1:8b via Ollama),
a cloud reference model (gpt-5.2),
the current fine-tuned local model (self-improving loop).

Candidates were scored by (1) deterministic checks (format compliance, label match, feature grounding), (2) an LLM-as-a-judge, and — for a subset — (3) pairwise comparison by human experts; the highest-scoring explanation per flow was kept as the training target.

Format

training_dataset.jsonl — one chat-format record per line:

{"messages": [
  {"role": "system", "content": "You are a network security expert..."},
  {"role": "user", "content": "Analyze this network traffic...\n\nCurrent flow:\n{...}"},
  {"role": "assistant", "content": "LABEL:\n...\n\nREASONING:\n...\n\nSOLUTION:\n..."}
]}

training_dataset.json contains the same examples with additional metadata (source file, predicted/actual label, raw flow features).

Source

Flow features are derived from CICIDS2017 (Sharafaldin, Lashkari & Ghorbani, 2018). Please also credit the original dataset when using this derived data.

Citation

If you use this dataset, please cite the thesis (mmalensek/SNIC_Network_Security).

Authors

Martin Malenšek — author. Mentor: izr. prof. dr. Veljko Pejović. Co-mentor: asist. Miha Grohar.

Downloads last month: 33

Total file size:

67.2 MB