Network-Level Spam Defenses

Nick FeamsterGeorgia Tech

with Anirudh Ramachandran, Shuang Hao, Alex Gray, Santosh Vempala

2

Spam: More than Just a Nuisance

• 95% of all email traffic– Image and PDF Spam

(PDF spam ~12%)

• As of August 2007, one in every 87 emails constituted a phishing attack

• Targeted attacks on the rise– 20k-30k unique phishing attacks per month

Source: CNET (January 2008), APWG

3

Approach: Filter

• Prevent unwanted traffic from reaching a user’s inbox by distinguishing spam from ham

• Question: What features best differentiate spam from legitimate mail?– Content-based filtering: What is in the mail?– IP address of sender: Who is the sender?– Behavioral features: How the mail is sent?

Conventional: Content Filters• Trying to hit a moving target...

...and even mp3s!

PDFs Excel sheets Images

5

Problems with Content Filtering• Customized emails are easy to generate: Content-

based filters need fuzzy hashes over content, etc.

• Low cost to evasion: Spammers can easily alter features of an email’s content can be easily adjusted and changed

• High cost to filter maintainers: Filters must be continually updated as content-changing techniques become more sophisticated

6

Another Approach: IP Addresses

• Problem: IP addresses are ephemeral

• Every day, 10% of senders are from previously unseen IP addresses

• Possible causes– Dynamic addressing– New infections

7

Our Idea: Network-Based Filtering

• Filter email based on how it is sent, in addition to simply what is sent.

• Network-level properties are less malleable– Network/geographic location of sender and receiver– Set of target recipients– Hosting or upstream ISP (AS number)– Membership in a botnet (spammer, hosting

infrastructure)

8

Why Network-Level Features?

• Lightweight: Don’t require inspecting details of packet streams– Can be done at high speeds– Can be done in the middle of the network

• Robust: Perhaps more difficult to change some network-level features than message contents

9

Challenges (Talk Outline)• Understanding network-level behavior

– What network-level behaviors do spammers have?– How well do existing techniques work?

• Building classifiers using network-level features– Key challenge: Which features to use?– Two Algorithms: SNARE and SpamTracker

• Building the system – Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there

10

Some Questions of Study

• Where (in IP space, in geography) does spam originate from?

• What OSes are used to send spam?

• What techniques are used to send spam?

11

Data: Spam and BGP• Spam Traps: Domains that receive only spam• BGP Monitors: Watch network-level reachability

Domain 1

Domain 2

17-Month Study: August 2004 to December 2005

12

Data Collection: MailAvenger• Configurable SMTP server• Collects many useful statistics

13

Finding: BGP “Spectrum Agility”• Hijack IP address space using BGP• Send spam• Withdraw IP address

A small club of persistent players appears to be using

this technique.

Common short-lived prefixes and ASes

61.0.0.0/8 4678 66.0.0.0/8 2156282.0.0.0/8 8717

~ 10 minutes

Somewhere between 1-10% of all spam (some clearly intentional,

others might be flapping)

14

Spectrum Agility: Big Prefixes?

• Flexibility: Client IPs can be scattered throughout dark space within a large /8– Same sender usually returns with different IP

addresses

• Visibility: Route typically won’t be filtered (nice and short)

15

Other Findings

• Top senders: Korea, China, Japan– Still about 40% of spam coming from U.S.

• More than half of sender IP addresses appear less than twice

• ~90% of spam sent to traps from Windows

16

How Well do IP Blacklists Work?

• Completeness: The fraction of spamming IP addresses that are listed in the blacklist

• Responsiveness: The time for the blacklist to list the IP address after the first occurrence of spam

17

Completeness and Responsiveness

• 10-35% of spam is unlisted at the time of receipt• 8.5-20% of these IP addresses remain unlisted

even after one month

Data: Trap data from March 2007, Spamhaus from March and April 2007

18

What’s Wrong with IP Blacklists?• Based on ephemeral identifier (IP address)

– More than 10% of all spam comes from IP addresses not seen within the past two months

• Dynamic renumbering of IP addresses• Stealing of IP addresses and IP address space• Compromised machines

• IP addresses of senders have considerable churn

• Often require a human to notice/validate the behavior– Spamming is compartmentalized by domain and not analyzed

across domains

19

Are There Other Approaches?

• Option 1: Stronger sender identity [AIP, Pedigree]

– Stronger sender identity/authentication may make reputation systems more effective

– May require changes to hosts, routers, etc.

• Option 2: Behavior-based filtering [SNARE, SpamTracker]

– Can be done on today’s network– Identifying features may be tricky, and some may

require network-wide monitoring capabilities

20

Outline

• Understanding the network-level behavior– What behaviors do spammers have?– How well do existing techniques work?

• Classifiers using network-level features– Key challenge: Which features to use?– Two algorithms: SNARE and SpamTracker

• The System: SpamSpotter – Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there

21

Finding the Right Features

• Goal: Sender reputation from a single packet?– Low overhead– Fast classification– In-network– Perhaps more evasion resistant

• Key challenge– What features satisfy these properties and can

distinguish spammers from legitimate senders?

22

Set of Network-Level Features• Single-Packet

– AS of sender’s IP– Distance to k nearest senders– Status of email service ports– Geodesic distance– Time of day

• Single-Message– Number of recipients– Length of message

• Aggregate (Multiple Message/Recipient)

23

Sender-Receiver Geodesic Distance

90% of legitimate messages travel 2,200 miles or less

24

Density of Senders in IP Space

For spammers, k nearest senders are much closer in IP space

25

Local Time of Day at Sender

Spammers “peak” at different local times of day

26

Combining Features: RuleFit• Put features into the RuleFit classifier• 10-fold cross validation on one day of query logs

from a large spam filtering appliance provider

• Comparable performance to SpamHaus– Incorporating into the system can further reduce FPs

• Using only network-level features• Completely automated

27

SNARE: Putting it Together

• Email arrival• Whitelisting

– Top 10 ASes responsible for 43% of misclassified IP addresses• Greylisting• Retraining

28

Benefits of Whitelisting

Whitelisting top 50 ASes:False positives reduced to 0.14%

29

Outline• Understanding the network-level behavior

– What behaviors do spammers have?– How well do existing techniques work?

• Classifiers using network-level features– Key challenge: Which features to use?– Algorithms: SNARE and SpamTracker

• Building the system (SpamSpotter)– Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there

30

SpamTracker

• Idea: Blacklist sending behavior (“Behavioral Blacklisting”)– Identify sending patterns commonly used by

spammers

• Intuition: Much more difficult for a spammer to change the technique by which mail is sent than it is to change the content

31

SpamTracker: Clustering Approach

• Construct a behavioral fingerprint for each sender

• Cluster senders with similar fingerprints• Filter new senders that map to existing

clusters

32

SpamTracker: Identify Invariant

domain1.com domain2.com domain3.com

spam spam spam

IP Address: 76.17.114.xxxKnown Spammer

DHCPReassignment

Behavioral fingerprint

domain1.com domain2.com domain3.com

spam spam spam

IP Address: 24.99.146.xxxUnknown sender

Cluster on sending behavior

Similar fingerprint!

Cluster on sending behavior

Infection

33

Building the Classifier: Clustering

• Feature: Distribution of email sending volumes across recipient domains

• Clustering Approach– Build initial seed list of bad IP addresses– For each IP address, compute feature vector:

volume per domain per time interval– Collapse into a single IP x domain matrix:– Compute clusters

34

Clustering: Output and Fingerprint

• For each cluster, compute fingerprint vector:

• New IPs will be compared to this “fingerprint”

IP x IP Matrix: Intensity indicates pairwise similarity

35

Evaluation

• Emulate the performance of a system that could observe sending patterns across many domains– Build clusters/train on given time interval

• Evaluate classification– Relative to labeled logs– Relative to IP addresses that were eventually listed

36

Data• 30 days of Postfix logs from email hosting service

– Time, remote IP, receiving domain, accept/reject– Allows us to observe sending behavior over a large

number of domains– Problem: About 15% of accepted mail is also spam

• Creates problems with validating SpamTracker

• 30 days of SpamHaus database in the month following the Postfix logs– Allows us to determine whether SpamTracker detects

some sending IPs earlier than SpamHaus

37

Clustering ResultsHam

Spam

SpamTracker Score

Separation may not be sufficient alone, but could be a useful feature

38

Outline• Understanding the network-level behavior

– What behaviors do spammers have?– How well do existing techniques work?

• Building classifiers using network-level features– Key challenge: Which features to use?– Algorithms: SpamTracker and SNARE

• Building the system (SpamSpotter)– Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there

39

Deployment: Real-Time Blacklist

• As mail arrives, lookups received at BL

• Queries provide proxy for sending behavior

• Train based on received data

• Return score

Approach

40

Challenges• Scalability: How to collect and aggregate data, and form

the signatures without imposing too much overhead?

• Dynamism: When to retrain the classifier, given that sender behavior changes?

• Reliability: How should the system be replicated to better defend against attack or failure?

• Evasion resistance: Can the system still detect spammers when they are actively trying to evade?

41

Design Choice: Augment DNSBL• Expressive queries

– SpamHaus: $ dig 55.102.90.62.zen.spamhaus.org• Ans: 127.0.0.3 (=> listed in exploits block list)

– SpamSpotter: $ dig \ receiver_ip.receiver_domain.sender_ip.rbl.gtnoise.net

• e.g., dig 120.1.2.3.gmail.com.-.1.1.207.130.rbl.gtnoise.net

• Ans: 127.1.3.97 (SpamSpotter score = -3.97)

• Also a source of data– Unsupervised algorithms work with unlabeled

data

42

Latency

Performance overhead is negligible.

43

Design Choice: Sampling

Relatively small samples can achieve low false positive rates

44

Possible Improvements• Accuracy

– Synthesizing multiple classifiers– Incorporating user feedback– Learning algorithms with bounded false positives

• Performance– Caching/Sharing– Streaming

• Security– Learning in adversarial environments

45

Summary: Network-Based Behavioral Reputation

• Spam increasing, spammers becoming agile– Content filters are falling behind– IP-Based blacklists are evadable

• Up to 30% of spam not listed in common blacklists at receipt. ~20% remains unlisted after a month

• Complementary approach: behavioral blacklisting based on network-level features– Key idea: Blacklist based on how messages are sent– SNARE: Automated sender reputation

• ~90% accuracy of existing with lightweight features– SpamTracker: Spectral clustering

• catches significant amounts faster than existing blacklists– SpamSpotter: Putting it together in an RBL system

46

Next Steps: Phishing and Scams

• Scammers host Web sites on dynamic scam hosting infrastructure– Use DNS to redirect users to different sites

when the location of the sites move• State of the art: Blacklist URL• Our approach: Blacklist based on

network-level fingerprints

Konte et al., “Dynamics of Online Scam Hosting Infrastructure”, PAM 2009

47

References• Anirudh Ramachandran and Nick Feamster, “Understanding

the Network-Level Behavior of Spammers”, ACM SIGCOMM, 2006

• Anirudh Ramachandran, Nick Feamster, and Santosh Vempala, “Filtering Spam with Behavioral Blacklisting”, ACM CCS, 2007

• Nadeem Syed, Shuang Hao, Nick Feamster, Alex Gray and Sven Krasser, “SNARE: Spatio-temporal Network-level Automatic Reputation Engine”, GT-CSE-08-02

• Anirudh Ramachandran, Shuang Hao, Hitesh Khandelwal, Nick Feamster, Santosh Vempala, “A Dynamic Reputation Service for Spotting Spammers”, GT-CS-08-09 (In submission)

48

Time Between Record ChangesFast-flux Domains tend to change much more frequently than legitimately hosted sites

49

50

Classifying IP Addresses

• Given “new” IP address, build a feature vector based on its sending pattern across domains

• Compute the similarity of this sending pattern to that of each known spam cluster– Normalized dot product of the two feature vectors– Spam score is maximum similarity to any cluster

51

Sampling: Training Time

52

Additional History: Message Size Variance

Senders of legitimate mail have a much higher variance in sizes of messages they send

Message Size Range

Certain Spam

Likely Spam

Likely Ham

Certain Ham

Surprising: Including this feature (and others with more history) can actually decrease the accuracy of the classifier

53

Completeness of IP Blacklists

~80% listed on average

~95% of bots listed in one or more blacklists

Number of DNSBLs listing this spammer

Only about half of the IPs spamming from short-lived BGP are listed in any blacklistFr

actio

n of

all

spam

rece

ived

Spam from IP-agile senders tend to be listed in fewer blacklists

54

Low Volume to Each Domain

Lifetime (seconds)

Am

ount

of S

pam Most spammers send very little spam, regardless

of how long they have been spamming.

55

Some Patterns of Sending are Invariant

domain1.com domain2.com domain3.com

spam spam spam

IP Address: 76.17.114.xxx

DHCPReassignment

domain1.com domain2.com domain3.com

spam spam spam

IP Address: 24.99.146.xxx

• Spammer's sending pattern has not changed• IP Blacklists cannot make this connection

56

Characteristics of Agile Senders

• IP addresses are widely distributed across the /8 space• IP addresses typically appear only once at our sinkhole• Depending on which /8, 60-80% of these IP addresses

were not reachable by traceroute when we spot-checked

• Some IP addresses were in allocated, albeit unannounced space

• Some AS paths associated with the routes contained reserved AS numbers

57

Early Detection Results

• Compare SpamTracker scores on “accepted” mail to the SpamHaus database– About 15% of accepted mail was later determined to

be spam– Can SpamTracker catch this?

• Of 620 emails that were accepted, but sent from IPs that were blacklisted within one month– 65 emails had a score larger than 5 (85th percentile)

58

Evasion

• Problem: Malicious senders could add noise– Solution: Use smaller number of trusted domains

• Problem: Malicious senders could change sending behavior to emulate “normal” senders– Need a more robust set of features…