machine learning & security. detect atypical behaviour in logs

27
Detect atypical behaviour in logs

Upload: alexander-melnychuk

Post on 16-Apr-2017

112 views

Category:

Data & Analytics


0 download

TRANSCRIPT

Page 1: Machine learning & security. Detect atypical behaviour in logs

Machine Learning & Security. Detect atypical behaviour in

logs

Page 2: Machine learning & security. Detect atypical behaviour in logs

The more experiments you make, the better

Page 3: Machine learning & security. Detect atypical behaviour in logs

All these busters!

Page 4: Machine learning & security. Detect atypical behaviour in logs

The data is correct, sir...

Page 5: Machine learning & security. Detect atypical behaviour in logs

It must be here somewhere… I’ve seen it!

Page 6: Machine learning & security. Detect atypical behaviour in logs

We have a great solution for you!

Page 7: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?

Page 8: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?1. Clean out log file

Page 9: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?1. Clean out log file

2. Prepare data for clusterization

Page 10: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?1. Clean out log file

2. Prepare data for clusterization

3. Clusterize data

Page 11: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?1. Clean out log file

2. Prepare data for clusterization

3. Clusterize data

4. “Picture of Normality”

Page 12: Machine learning & security. Detect atypical behaviour in logs

How it works? Magic?1. Clean out log file

2. Prepare data for clusterization

3. Clusterize data

4. “Picture of Normality”

5. Doing some Machine Learning magic ;)

Page 13: Machine learning & security. Detect atypical behaviour in logs

Now it’s clean and nice like baby’s ass!

Page 14: Machine learning & security. Detect atypical behaviour in logs

You see words. I see numbers.

AppInfo connection accepted DeviceName TCPPid IPAddr Port Device Controller

Stopping SdlTCPConnection:

AppInfo RISCMAccess DeviceTransientConnection

AppInfo Closing Station connection Error Description transition defined input

AppInfo StationInit EnblocCall calledParty

0.4567 0.4756 0.4070 0.40230.2546 0.5879 0.3546 0.5467 0.45680.6543 0.3684:0.2365 0.34560.3654 0.24680.6734 0.3756 0.5867 0.14650.7845 0.3765 0.2365 0.7986 0.34630.4768 0.3758 0.4976 0.3756

Page 15: Machine learning & security. Detect atypical behaviour in logs

I don’t need that piece of junk!

score() = effectiveness

% of featuresjunk

Page 16: Machine learning & security. Detect atypical behaviour in logs

Total annihi… Clusterization!

KNN algorithm(K Nearest Neighbors)

Page 17: Machine learning & security. Detect atypical behaviour in logs

No train no gain.

picture of normality

Page 18: Machine learning & security. Detect atypical behaviour in logs

Freeze! You’re busted, buddy. I’m a cop.

Detected anomalies

Page 19: Machine learning & security. Detect atypical behaviour in logs

I’m watching you, loosers

Page 20: Machine learning & security. Detect atypical behaviour in logs

Let me look at you closer, boy

$ nc 202.41.76.251 80

nmap -A -T4 74.207.244.221

nikto -verbose -host google.com

Page 21: Machine learning & security. Detect atypical behaviour in logs

When in doubt, use brute force

BruteForcing

Page 22: Machine learning & security. Detect atypical behaviour in logs

It’s not a DDoS, it’s an “Aggressive Scan”!

DDoS attacks

Page 23: Machine learning & security. Detect atypical behaviour in logs

Smart? Dumb? What do you prefer?

for fuzz in range(255): packet=‘\x80\x00\x00’+chr(fuzz)+’\x01\x00\x00\x00’

sock = socket.socket(socket.AF_INET, 1)sock.connect((IP, PORT))sock.send(packet)

FUZZING

Page 24: Machine learning & security. Detect atypical behaviour in logs

Money talks. But all mine ever says is “Bye!”

Suspicious financial transactions

Page 25: Machine learning & security. Detect atypical behaviour in logs

What do you mean I owe you 10.000 $ ???

Toll fraud

Page 26: Machine learning & security. Detect atypical behaviour in logs

C’mon, kid, I’ll show you smth bad

Page 27: Machine learning & security. Detect atypical behaviour in logs

Thank You!

THE END

@[email protected]