1

Towards Anomaly/Intrusion

Detection and Mitigation on High-Speed Networks

Yan Gao, Zhichun Li, Manan Sanghi, Yan Chen, Ming-Yang Kao

Northwestern Lab for Internet and Security Technology (LIST)

Department of Computer ScienceNorthwestern University

http://list.cs.northwestern.edu

2

Outline• Motivation• Architecture of RAIDM• Statistical Sketch-based

Anomaly/Intrusion Detection– Design– Evaluation Results

• Polymorphic Worm Signature Generation with Provable Attack Resilience– Design– Preliminary Evaluation Results

• Conclusions

3Desired Features of Intrusion Detection Systems (IDS)

• Network-based and scalable to high-speed links– Slammer worm infected 75,000 machines in <10 mins– Flash worm can take less than 1 second to compromise

1M vulnerable machines in the Internet [Staniford04]– Host-based schemes inefficient and user dependent

» Have to install IDS on all user machines !

– Existing network IDS unscalable: In a 10Gbps link, each 40-byte packet only has 32ns for processing !

• Aggregated detection over multiple vantage points– Multi-homing, load balancing, policy routing become

popular asymmetric routing– Even worse… Per-packet load balancing– Cannot afford to move traffic around

4Features of Demanded Intrusion Detection Systems (IDS)

• Attack resiliency– Human adversaries are difficult to handle. Attacks

tend to fool or DoS the IDS system.– Many IDSs use exact per-flow states, which is

vulnerable to DoS attack.

• Attack root cause analysis for mitigation– Detection is only the first step. We also need

mitigation and prevention.– Overall traffic based approaches can scale to high

speed but cannot really help mitigation– We need flow-level information for mitigation– Signature generation for polymorphic worms

5

Outline• Motivation• Architecture of RAIDM• Statistical Sketch-based

Anomaly/Intrusion Detection– Design– Evaluation Results

• Polymorphic Worm Signature Generation with Provable Attack Resilience– Design– Preliminary Evaluation Results

• Conclusions

6Router-based Anomaly/Intrusion Detection and Mitigation System

(RAIDM)• Online traffic recording

– Design reversible sketch for data streaming computation– Record millions of flows (GB traffic) in a few hundred KB

• Online flow-level anomaly/intrusion detection & mitigation

– As a first step, detect TCP SYN flooding, horizontal and vertical scans even when mixed

» Existing schemes like TRW/AC, CPM will have high false positives

– Infer key characteristics of malicious flows for mitigation

• Dos attack resiliency• Apply to distributed detection environment

RAIDM: First flow-level intrusion detection that can sustain 10s Gbps bandwidth even for worst case traffic of 40-byte packet streams

7Router-based Anomaly/Intrusion Detection and Mitigation System

(RAIDM)• Attach to routers as a black box

Router

LAN

Internet

Switch

(a)

Router

LAN

(b)

RAIDMsystem

scan

po

rtsc

an

port

Splitter

Router

(c)

Splitter

HAIDMsystem

RA

IDM

syst

em

RAIDMsystem

Switch

Switch

Switch

Switch

Switch

LAN

LAN

LAN

LAN

InternetInternet

Attach HRAID black boxes to high-speed routers (a) original configuration, (b) distributed configuration for which each port is monitored separately, (c) aggregate configuration for which a splitter is used to aggregate the traffic from all the ports of a router.

8

Reversiblek-ary sketch monitoring

Filtering

Sketch based statistical anomaly detection (SSAD)

Local sketch records

Sent out for aggregation

Remote aggregatedsketchrecords

Per-flow monitoring

Streaming packet data

Normal flows

Suspicious flows

Intrusion or anomaly alarms

Keys of suspicious flows

Keys of normal flows

Data path Control pathModules on the critical path

Signature-based detection

Polymorphic worm detection (Hamsa)

Part ISketch-basedmonitoring & detection

Part IIPer-flowmonitoring & detection

Modules on the non-critical path

Network fault diagnosis (DOD)

RAIDM Architecture

9

Outline• Motivation• Architecture of RAIDM• Statistical Sketch-based

Anomaly/Intrusion Detection– Design– Evaluation Results

• Polymorphic Worm Signature Generation with Provable Attack Resilience– Design– Preliminary Evaluation Results

• Conclusions

10Statistical Sketch-based Anomaly/Intrusion Detection

(SSAD)

• Recording stage: record traffic of each router with different sketches, then transfer and combine them to current reversible sketch.

• Detection stage: use Time Series Analysis (Holt-Winter and EWMA) to detect large forecast error as anomalies.

• False positive reduction & 2D sketch skipped (lack of time)

Sketch recording

Current reversible

sketch

Forecast sketch

Real traffic stream

Attack mitigation

Update

Forecast error

Statistical detection

Aggregate Two

dimensional sketch

False positive

reduction

Aggregate reversible

sketch

Sketches from other routers

...

Recording process Detection process

11Statistical Sketch-based Anomaly/Intrusion Detection

(SSAD)• Distributed Detection Environment

SYN/ACK1

SY

N1

Dept 1 Dept 2 Dept n

Router 1

Router 2

Router 3

…...

Internal Network

` ` `

SY

N/A

CK

2

SY

N2

12

Background: Reversible k-ary Sketch

• Array of hash tables: Tj[K] (j = 1, …, H)– Similar to count sketch, counting bloom filter,

multi-stage filter, …

• Update (k, u): Tj [ hj(k)] += u (for all j)

1

j

H

0 1 K-1…

……

1

j

H

0 1 K-1…

……

hj(k)

hH(k)

h1(k)

13

Background: Reversible k-ary Sketch

+ =

• Estimate v(S, k): sum of updates for key k• Sketches are linear

– Can Combine Sketches– Can aggregate data from different times, locations,

and sources

• Inference I(S, t): output the heavy keys whose values are larger than threshold t

14

• RS((DIP, Dport), SYN-SYN/ACK)• RS((SIP, DIP), SYN-SYN/ACK)• RS((SIP, Dport), SYN-SYN/ACK)

Attack types RS((DIP, Dport),

SYN-SYN/ACK)

RS((SIP, DIP),

SYN-SYN/ACK)

RS((SIP, Dport),

SYN-SYN/ACK)

SYN flooding Yes Yes Yes

Vertical scans No Yes No

Horizontal scans

No No Yes

Detection Algorithm

HORIZONTAL

PORT NUMBER

SOURCE IP

BLOCK

VERTICAL

15

DoS Resiliency Analysis• Possible DoS attack to existing approaches

like TRW and TRW/AC– Source spoofed SYN flooding attack– Source spoofed packets to random location

• Attack SSAD is difficult. Possible attack is based on creating collisions in sketches. But…– Reverse engineering of hash functions is difficult– The possibility of finding collisions through

exhaustive search is very low– Attacks are limited even with collisions: need the

cooperation with comprised internal hosts.

16

• Data Sets– NU traces (239M flows, 1.8TB traffic/day)– Lawrence Berkeley National Laboratory (LBL) Trace

(900M flows)

• Rest of results based on NU trace evaluation

• Scalability and memory usage– Total 9.4MB used for recording hundreds of millions

of flows» 3 reversible k-ary sketches, 2 two dimensional sketches and

1 original k-ary sketch

– Small # of memory access per packet

Evaluation

17

• Fast – Recording speed for the worst case traffic, all 40B pkts

» 16 Gbps on a single FPGA board» 526 Mbps on a Pentium-IV 2.4GHz PC

– Detection speed» On site NU experiment covering 1430 minutes: 0.34 sec for one

minute on average. (std=0.64 sec)

• Accurate Anomaly Detection w/ Reversible Sketch– Compared with detection using complete flow-level logs– Provable probabilistic accuracy guarantees– Even more accurate on real Internet traces

Evaluation (cont’d)

18Evaluation (cont’d)• 25 SYN flooding, 936 horizontal scans and 19 vertical scans

detected (after sketch-based false positive reduction)• 18 out of 25 SYN flooding verified w/ backscatter

– Complete flow-level connection info used for backscatter

• Scans verified (all for vscan, top and bottom 10 for hscan)– Unknown scans also found in DShield and other alert reports

Top 10 horizontal scans Bottom 10 horizontal scans

Description Dport count

SQLSnake 1433 5

W32.Rahack 4899 2

unknown scan 6101 1

Scan SSH 22 1

MySQL Bot scans 10202 1

Description Dport count

Sasser or Korgo worm 445 3

W32.Sasser.B.Worm 5554 1

Nachi or MSBlast worm 135 3

NetBIOS scan 139 3

19

Outline• Motivation• Architecture of RAIDM• Statistical Sketch-based

Anomaly/Intrusion Detection– Design– Evaluation Results

• Polymorphic Worm Signature Generation with Provable Attack Resilience– Design– Preliminary Evaluation Results

• Conclusions

20Requirements for polymorphic worm

signature generation• Network-based– Worm spread at exponential speed, at early stage

there are limited worm samples.– Keep up with the network speed !

• Noise tolerant– Most network level flow classifier may suffer false

positives.• Attack resilience

– Attackers always try to evade the signature generation system

• Efficient signature matching– Again, on high-speed networks!

• No existing work satisfies these requirements

21

Hamsa• Content based v.s. behavior based signature

– Content based: treat a worm as a byte sequence– Behavior based: the actual dynamics of the worm

execution– Fast matching could be a problem for behavior

based

• We propose Hamsa, a network-based signature generation system to meet the aforementioned requirements– Content based system (token based)– Accuracy comparable to the state-of-the art

technique [Polygraph] but much faster– Propose an adversary model and has attack

resilience guarantee

22

Hamsa Design

• Sniff traffic from networks• Assembly the packets to flows• Classify traffic based protocol• Filter out known worms• Generate suspicious and normal pools.

ProtocolClassifier

UDP1434

HamsaSignatureGenerator

WormFlow

Classifier

TCP137

. . .TCP80

TCP53

TCP25

NormalTraffic Pool

SuspiciousTraffic Pool

Signatures

NetworkTap

KnownWormFilter

23

Hamsa Design

• Iterative signature generation• Extract the tokens form suspicious pool• Identify the same set of tokens in normal pool• Core part: greedy algorithm based on the token information

Hamsa Signature Generator

TokenExtractor

TokenIdentification

Tokens

CoreSignature

FilterPool sizetoo small?

NO

SuspiciousTraffic Pool

NormalTraffic Pool

YES

Quit

24Model-based Polymorphic Worm Signature Generation Problem &

Algorithm

No noise: O(n) Noise: NP-Hard

The problem

The model

The algorithm

25

Evaluation Methodology• Data collection

– Normal pool:» 300MB Web traffic for training» 20GB Web traffic and Binary distribution of Linux for evaluation

– Suspicious pool:» 10 ~ 500 samples (with noise and different worms)» 5000 samples each worm as false negative testing data set

– Three pseudo worms: ATPhttpd, Apache-Knacker, Codered II– Two polymorphic engines from Internet

• Simulation settings– Single worm with noise

» Test pool size 100 and 200» Noise ratio 0, 10%, 30%, 50%

– Multiple worms with noise» 3 worms together: ATPhttpd, Apache-Knacker, Codered II» Test pool size 100 and 200» Noise ratio 0, 10% and 25%

26Preliminary Evaluation Results

• Signature Quality

• Signature Generation Speed– 64 ~ 361 times faster than Polygraph– Only use several seconds to at most minutes to generate

signatures

• Attack Resilience– Provable attack resilience (details omitted)– For token-fit attack, Polygraph fail but Hamsa succeed

27

Backup Slides

28

Intrusion Detection and Mitigation

Attacks detected MitigationDenial of Service (DoS), e.g., TCP SYN flooding

SYN defender, SYN proxy, or SYN cookie for victim

Port Scan and worms Ingress filtering with attacker IPVertical port scan Quarantine the victim machineHorizontal port scan Monitor traffic with the same

port # for compromised machine

Spywares Warn the end users being spied

HORIZONTAL

PORT NUMBER

SOURCE IP

BLOCK

VERTICAL

29

Reversible Sketch Based Anomaly Detection

• Input stream: (key, update) (e.g., SIP, SYN-SYN/ACK)

Sketchmodule

Forecastmodule(s)

Anomaly detectionmodule

(k,u) … SketchesError

Sketch Alarms

• Report flows with large forecast errors• Infer the (characteristics) key for mitigation

• Summarize input stream using sketches

• Build forecast models on top of sketches

30Reducing False Positives for SYN Flooding Detection

• Reasons of false positives of SYN flooding detection– Network/server congestions/failtures– Polluted or outdated DNS entries

• Filters to reduce false positives caused by bursty network /server congestions/failures1.2. Lifetime > Thresholdlife

• Filters to reduce the false positives caused by misconfigurations or related problems– No connection history

2

1

#

/##

SYN

ACKSYNSYN

31Intrusion Classification with Two Dimensional Sketch

• We need to distinguish different types of attack to take the most effective mitigation scheme– However, one dimensional information is not

enough• Non-spoofed SYN flooding v.s. horizontal scan {SIP,DP}

– Bi-modal distribution.

• Two dimensional SketchStructure of 2D sketch

hx(SIP,DIP) hx(SIP,DIP) hx(SIP,DIP)

H two-dimensional hash matrix

hy(DP)

hy(DP)

hy(DP)

+1

hx(2.3.0.5,9.7.2.3)

hy(80)

Packet {2.3.0.5, 9.7.2.3, 80,SYN}Example UPDATE

32Intrusion Classification with Two Dimensional Sketch

• Two dimensional sketch is accurate– Refer to the paper about accuracy proof– Can archive 99.9956% detection rate by the

parameter mentioned in the paper

33

Automated worm signature generation

• Manual signature generation is too slow for fast propagated worms

• Automatic signature generation has been proposed [Earlybird][Autograph]

• But it is not hard for hackers to apply polymorphism to their worms.

• Polymorphic worm signature generation becomes necessary.