加密流量元数据与行为分析

EncGuard Pro 加密通信恶意行为检测平台

检测模式：规则检测 + 分类模型 + 异常检测 + 攻击链融合 模型状态：已启用

Alert Detail

告警详情

runtime-e0502fb5-1f2c-4bdb-8e54-5dc38ee3ded5

模型预测与异常检测已拆分为 model_prediction 与 anomaly_result 两个解释区。

风险评分 88 high
Basic Info

基础信息

event_id
runtime-e0502fb5-1f2c-4bdb-8e54-5dc38ee3ded5
flow_id
safe-lab-20260704092453-e82171-024-post_bruteforce_action_like
src_ip
10.20.7.81
dst_ip
203.0.113.211
protocol
ssh
timestamp
2026-07-04T09:24:55.493068+00:00
风险等级
high
检测类型
post_bruteforce_action
detectors
rule_engine, attack_chain
source
mixed_scenario_lab
chain_related
True
Risk Score

风险评分

final_risk_score
88
severity
high
security_alert
True
Risk Formation

最终风险形成

rule_score
88
supervised_risk_score
3
calibrated_risk_score
3
anomaly_risk_score
13
final_risk_score
88
fusion_policy
max(rule_score, calibrated_risk_score, anomaly_risk_score)
gate_formula
risk=(1-g)*supervised_risk+g*anomaly_risk
Weak Scenario Support

弱覆盖场景补强证据

scenarios
post_bruteforce_action
support_type
rule_anomaly_gate_attack_chain_supported
model_claim
not_strong_supervised_label
explanation
This scenario is supported by rules, anomaly detection, uncertainty gate, and chain evidence rather than claimed as a strongly supervised classifier label.
Model Prediction

模型预测 model_prediction

predicted_label
benign
malicious_probability
0.027
model_score
3
calibrated_risk_score
3
uncertainty_gate
0.033232
probability_entropy
0.143057
top2_margin
0.943232
js_divergence
0.00367
unknown_decision
False
model_supported_label
True

该场景主要由规则、攻击链或异常检测补强，不应表述为当前模型可靠覆盖。

Anomaly Detection

异常检测 anomaly_result

anomaly_score
13.070052
anomaly_risk_score
13
is_anomaly
False
Rule Hits

规则 evidence

post_bruteforce_action scenario_rule_engine · risk_score=88
Evidence

推荐处置 recommendation

  • uploaded_file=mixed_scenario_features.csv
  • input_label=post_bruteforce_action
  • uploaded feature row evaluated by EncGuard scenario rule engine
  • uncertainty_gate=0.033232
  • safe_lab_batch=safe-lab-20260704092453-e82171
  • scenario=post_bruteforce_action_like
  • ground_truth_label=post_bruteforce_action
  • safe synthetic metadata only; no payload and no real attack execution

recommendation：Review uploaded feature context and validate whether this communication is authorized.

Attack Chain

攻击链关联 attack_chain

ssh_bruteforce_to_post_action chain_id=inferred-1 · risk_score=88
post_action_to_encrypted_tunnel chain_id=inferred-2 · risk_score=95
Safety Boundary

安全边界说明

  • EncGuard 不解密 SSH/TLS/HTTPS/SFTP/SCP payload。
  • 当前检测依据为连接元数据、流量统计、规则 evidence、模型预测、异常检测和攻击链聚合。
  • post_bruteforce_action、encrypted_tunnel、data_exfiltration 主要由规则、攻击链或异常检测补强。
Raw Feature

原始特征详情

flow_id
safe-lab-20260704092453-e82171-024-post_bruteforce_action_like
src_ip
10.20.7.81
dst_ip
203.0.113.211
src_port
58834
dst_port
22
protocol
ssh
start_time
2026-07-04T09:45:22Z
duration
2.0932
total_packets
12
total_bytes
1098
fwd_packets
9
bwd_packets
3
fwd_bytes
818
bwd_bytes
280
upload_download_ratio
2.921429
packets_per_second
5.732805
bytes_per_second
524.551633
packet_size_mean
91.5
packet_size_std
3.100245
iat_mean
0.043736
iat_std
0.007139
same_src_conn_count_1min
34
same_src_conn_count_5min
78
short_connection_count_5min
57
long_session_flag
False
large_upload_flag
False
unknown_destination_flag
False
non_working_hour_flag
True
packet_direction_sequence_summary
short_client_initiated_bursts
packet_size_sequence_summary
small_repeated_handshake_like
burst_count
19
interactive_gap_mean
0.043736
interactive_gap_std
0.007139
post_login_long_session_flag
False
command_like_burst_flag
True
failed_login_then_long_session_flag
False
scenario
post_bruteforce_action_like
label
post_bruteforce_action
Related Events

相关事件