Beacon Traffic Based on Common User Agent Only Visiting Limited Number of Rare Domains

let timeframe = 2*1d;
let RuleId = "0027";
let DedupFields = dynamic(["SourceUserName", "RequestClientApplication"]); // Timeframe during which to search for beaconing behavior.
let lookback = 7d; // Lookback period to find if browser was used for other domains by user.
let min_requests=50; // Minimum number of requests to consider it beacon traffic.
let min_hours=8; // Minimum number of different hours during which connections were made to consider it beacon traffic.
let trusted_user_count=10; // If visited by this many users a domain is considered 'trusted'.
let max_sites=3; // Maximum number of different sites visited using this user-agent.
// Environment-specific query to obtain 'browser-like' traffic from proxy logs.
let BrowserTraffic = (p:timespan) {
CommonSecurityLog
| where DeviceVendor == "Zscaler" and DeviceProduct == "NSSWeblog"
| where (RequestClientApplication startswith "Mozilla/" and RequestClientApplication contains "Gecko")
};
let CommonDomains = BrowserTraffic(timeframe)
| summarize source_count=dcount(SourceUserName) by DestinationHostName
| where source_count>trusted_user_count
| project DestinationHostName;
let CommonUA = BrowserTraffic(timeframe)
| summarize source_count=dcount(SourceUserName), host_count=dcount(DestinationHostName) by RequestClientApplication
| where source_count>trusted_user_count and host_count > 100 // Normal browsers are browsers used by many people and visiting many different sites.
| project RequestClientApplication;
// Find browsers that are common, i.e., many users use them and they use them to visit many different sites.
// But some users only use the browser to visit a very limited set of sites.
// These are considered suspicious - since they might be an attacker masquerading a beacon as a legitimate browser.
let SuspiciousBrowers = BrowserTraffic(timeframe)
| where RequestClientApplication in(CommonUA)
| summarize BrowserHosts=make_set(DestinationHostName),request_count=count() by RequestClientApplication, SourceUserName
| where array_length(BrowserHosts) <= max_sites and request_count >= min_requests
| project RequestClientApplication, SourceUserName,BrowserHosts;
// Just reporting on suspicious browsers gives too many false positives.
// For example users that have the browser open on the login screen of 1 specific application.
// In the suspicious browsers we can search for beacon-like behavior.
// Get all browser traffic by the suspicious browsers.
let PotentialAlerts=SuspiciousBrowers
| join BrowserTraffic(timeframe) on RequestClientApplication, SourceUserName
// Find beaconing-like traffic - i.e., contacting the same host in many different hours.
| summarize hour_count=dcount(bin(TimeGenerated,1h)), BrowserHosts=any(BrowserHosts), request_count=count() by RequestClientApplication, SourceUserName, DestinationHostName
| where hour_count >= min_hours and request_count >= min_requests
// Remove common domains like login.microsoft.com.
| join kind=leftanti CommonDomains on DestinationHostName
// Begin environment-specific filter.
// End environment-specific filter.
| summarize RareHosts=make_set(DestinationHostName), TotalRequestCount=sum(request_count), BrowserHosts=any(BrowserHosts) by RequestClientApplication, SourceUserName
// Remove browsers that visit any common domains.
| where array_length(RareHosts) == array_length(BrowserHosts);
// Look back for 7 days to see the browser was not used to visit more hosts.
// This is to get rid of someone that started up the browser a long time ago and left only a single tab open.
PotentialAlerts
| join BrowserTraffic(lookback) on SourceUserName, RequestClientApplication
| summarize RareHosts=any(RareHosts),BrowserHosts1d=any(BrowserHosts),BrowserHostsLookback=make_set(DestinationHostName) by SourceUserName, RequestClientApplication
| where array_length(RareHosts) == array_length(BrowserHostsLookback)
// Begin de-duplication logic.
| extend DedupFieldValues=pack_all()
| mv-apply e=DedupFields to typeof(string) on (
    extend DedupValue=DedupFieldValues[tostring(e)]
| order by e // Sorting is required to ensure make_list is deterministic.
| summarize DedupValues=make_list(DedupValue)
)
| extend DedupEntity=strcat_array(DedupValues, "
| ")
| project-away DedupFieldValues, DedupValues
| join kind=leftanti (
    SecurityAlert
| where AlertName has RuleId and ProviderName has "ASI"
| where TimeGenerated >= ago(timeframe)
| extend DedupEntity = tostring(parse_json(tostring(parse_json(ExtendedProperties)["Custom Details"])).DedupEntity[0])
| project DedupEntity
) on DedupEntity
// End de-duplication logic.