Network-Level Spam Filtering Nick Feamster Georgia Tech with Anirudh Ramachandran, Shuang Hao, Maria...
-
Upload
jessica-mcleod -
Category
Documents
-
view
215 -
download
2
Transcript of Network-Level Spam Filtering Nick Feamster Georgia Tech with Anirudh Ramachandran, Shuang Hao, Maria...
Network-Level Spam Filtering
Nick FeamsterGeorgia Tech
with Anirudh Ramachandran, Shuang Hao, Maria Konte, Nadeem Syed, Alex Gray, Santosh Vempala, Jaeyeon Jung
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
Filtering
• 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 Approach: Content Filters
• Trying to hit a moving target...
...and even mp3s!
PDFs Excel sheets Images
5
Problems with Content Filtering
• Low cost to evasion: Spammers can easily alter features of an email’s content can be easily adjusted and changed
• Customized emails are easy to generate: Content-based filters need fuzzy hashes over content, etc.
• 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
Problem: Addresses Keep ChangingF
ract
ion
of
IP A
dd
ress
es
About 10% of IP addresses never seen before in trace
8
Key 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– Set of target recipients– Hosting or upstream ISP (AS number)– Membership in a botnet (spammer, hosting
infrastructure)– Network location of sender and receiver
9
Challenges (Talk 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?– Two Algorithms: SpamTracker and SNARE
• Building the system – Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there
10
Understanding the Network-Level Behavior of Spammers
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
• Highly configurable SMTP server• Collects many useful statistics
13
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
Why Such Big Prefixes?
• Visibility: Route typically won’t be filtered (nice and short)
• Flexibility: Client IPs can be scattered throughout dark space within a large /8– Same sender usually returns with different IP
addresses
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
What about IP-based blacklists?
17
Two Metrics
• 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
18
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
19
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
20
How to Fix This Problem?
• Option 1: Stronger sender identity– Stronger sender identity/authentication may make
reputation systems more effective– May require changes to hosts, routers, etc.
• Option 2: Filtering based on sender behavior– Can be done on today’s network– Identifying features may be tricky, and some may
require network-wide monitoring capabilities
21
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
22
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
23
SpamTracker Approach
• Construct a behavioral fingerprint for each sender
• Cluster senders with similar fingerprints
• Filter new senders that map to existing clusters
24
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
25
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
26
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
27
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
28
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
29
Classification ResultsHam
Spam
SpamTracker Score
Not always so accurate!
30
Improving Classification
• Lower overhead• Faster detection• Better robustness (i.e., to evasion, dynamism)
• Use additional features and combine for more robust classification– Temporal: interarrival times, diurnal patterns– Spatial: sending patterns of groups of senders
31
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?– Two Algorithms: SpamTracker and SNARE
• Building the system – Dynamism: Behavior itself can change– Scale: Lots of email messages (and spam!) out there
32
SNARE: Automated Sender Reputation
• Goal: Sender reputation from a single packet?(or at least as little information as possible)– Lower overhead– Faster classification– Less malleable
• Key challenge– What features satisfy these properties and can
distinguish spammers from legitimate senders
33
Sender-Receiver Geodesic Distance
90% of legitimate messages travel 2,200 miles or less
34
Density of Senders in IP Space
For spammers, k nearest senders are much closer in IP space
35
Local Time of Day at Sender
Spammers “peak” at different local times of day
36
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
• Using only network-level features• Completely automated
37
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
38
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
39
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?
40
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
41
Design Choice: Sampling
Relatively small samples can achieve low false positive rates
42
Dynamism: Accuracy over Time
43
Improvements
• Accuracy– Synthesizing multiple classifiers– Incorporating user feedback– Learning algorithms with bounded false positives
• Performance– Caching/Sharing– Streaming
• Security– Learning in adversarial environments
44
Next Steps: Applications to Scams
• Scammers host Web sites on dynamic scam hosting infrastructure
• Use the 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
45
Example: Time Between Record Changes
Fast-flux Domains tend to change much more frequently than legitimately hosted sites
46
Summary: Network-Based Behavioral Filtering
• 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– Blacklist based on how messages are sent– SpamTracker: Spectral clustering
• catches significant amounts faster than existing blacklists– SNARE: Automated sender reputation
• ~90% accuracy of existing with lightweight features– SpamSpotter: Putting it together in an RBL system
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
48
49
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
50
Sampling: Training Time
51
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
52
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 blacklistF
ract
ion
of
all
spam
rec
eive
d
Spam from IP-agile senders tend to be listed in fewer blacklists
53
Low Volume to Each Domain
Lifetime (seconds)
Am
ou
nt
of
Sp
am
Most spammers send very little spam, regardless of how long they have been spamming.
54
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
55
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
56
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)
57
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…