User Interfaces and Algorithms for Fighting Phishing Jason I. Hong Carnegie Mellon University
Everyday Security Problems
Costs of Unusable Privacy & Security High Spyware, viruses, worms –Storm Worm Botnet
Costs of Unusable Privacy & Security High Spyware, viruses, worms –Storm Worm Botnet Too many passwords!!! Confidential information on laptops and mobile devices that are frequently lost or stolen
Usable Privacy and Security “Give end-users security controls they can understand and privacy they can control for the dynamic, pervasive computing environments of the future.” - Computing Research Association 2003
Everyday Privacy and Security Problem
This entire process known as phishing
Phishing is a Plague on the Internet Estimated 3.5 million people have fallen for phishing Estimated $350m-$2b direct losses a year unique phishing sites reported in June 2007 Easier (and safer) to phish than rob a bank
Project: Supporting Trust Decisions Goal: help people make better online trust decisions –Currently focusing on anti-phishing Large multi-disciplinary team project at CMU –Computer science, human-computer interaction, public policy, social and decision sciences, CERT
Our Multi-Pronged Approach Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm Automate where possible, support where necessary
Our Multi-Pronged Approach Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm What do users know about phishing?
Interview Study Interviewed 40 Internet users (35 non-experts) “Mental models” interviews included role play and open ended questions Brief overview of results (see paper for details) J. Downs, M. Holbrook, and L. Cranor. Decision Strategies and Susceptibility to Phishing. In Proceedings of the 2006 Symposium On Usable Privacy and Security, July 2006, Pittsburgh, PA.
Little Knowledge of Phishing Only about half knew meaning of the term “phishing” “Something to do with the band Phish, I take it.”
Little Attention Paid to URLs Only 55% of participants said they had ever noticed an unexpected or strange-looking URL Most did not consider them to be suspicious
Some Knowledge of Scams 55% of participants reported being cautious when asks for sensitive financial info –But very few reported being suspicious of asking for passwords Knowledge of financial phish reduced likelihood of falling for these scams –But did not transfer to other scams, such as an amazon.com password phish
Naive Evaluation Strategies The most frequent strategies don’t help much in identifying phish –This appears to be for me –It’s normal to hear from companies you do business with –Reputable companies will send s “I will probably give them the information that they asked for. And I would assume that I had already given them that information at some point so I will feel comfortable giving it to them again.”
Summary of Findings People generally not good at identifying scams they haven’t specifically seen before People don’t use good strategies to protect themselves Currently running large-scale survey across multiple cities in the US to gather more data Amazon also active in looking for fake domain names
Outline Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm Can we train people not to fall for phish?
Web Site Training Study Laboratory study of 28 non-expert computer users Asked participants to evaluate 20 web sites –Control group evaluated 10 web sites, took 15 min break to read or play solitaire, evaluated 10 more web sites –Experimental group same as above, but spent 15 min break reading web-based training materials Experimental group performed significantly better identifying phish after training –Less reliance on “professional-looking” designs –Looking at and understanding URLs –Web site asks for too much information People can learn from web-based training materials, if only we could get them to read them!
How Do We Get People Trained? Most people don’t proactively look for training materials on the web Companies send “security notice” s to employees and/or customers We hypothesized these tend to be ignored –Too much to read –People don’t consider them relevant –People think they already know how to protect themselves Led us to idea of embedded training
Embedded Training Can we “train” people during their normal use of to avoid phishing attacks? –Periodically, people get sent a training –Training looks like a phishing attack –If person falls for it, intervention warns and highlights what cues to look for in succinct and engaging format P. Kumaraguru, Y. Rhee, A. Acquisti, L. Cranor, J. Hong, and E. Nunge. Protecting People from Phishing: The Design and Evaluation of an Embedded Training System. CHI 2007.
Subject: Revision to Your Amazon.com Information Please login and enter your information Embedded training example
Intervention #1 – Diagram
Explains why they are seeing this message
Intervention #1 – Diagram Explains what a phishing scam is
Intervention #1 – Diagram Explains how to identify a phishing scam
Intervention #1 – Diagram Explains simple things you can do to protect self
Intervention #2 – Comic Strip
Embedded Training Evaluation #1 Lab study comparing our prototypes to standard security notices –Group A – eBay, PayPal notices –Group B – Diagram that explains phishing –Group C – Comic strip that tells a story 10 participants in each condition (30 total) –Screened so we only have novices Go through 19 s, 4 phishing attacks scattered throughout, 2 training s too –Role play as Bobby Smith at Cognix Inc
Embedded Training Results
Existing practice of security notices is ineffective Diagram intervention somewhat better –Though people still fell for final phish Comic strip intervention worked best –Statistically significant –Combination of less text, graphics, story?
Evaluation #2 New questions: –Have to fall for phishing to be effective? –How well do people retain knowledge? Roughly same experiment as before –Role play as Bobby Smith at Cognix Inc, go thru 16 s –Embedded condition means have to fall for our –Non-embedded means we just send the comic strip –Also had people come back after 1 week To appear in APWG eCrime Researchers’ Summit (Oct 4-5 at CMU)
Results of Evaluation #2 Have to fall for phishing to be effective? How well do people retain knowledge after a week?
Results of Evaluation #2 Have to fall for phishing to be effective? How well do people retain knowledge after a week? Correctness
Results of Evaluation #2 Have to fall for phishing to be effective? How well do people retain knowledge after a week? Correctness
Anti-Phishing Phil A game to teach people not to fall for phish –Embedded training focuses on –Our game focuses on web browser Goals –How to parse URLs –Where to look for URLs –Use search engines for help Try the game! –
Anti-Phishing Phil
Evaluation of Anti-Phishing Phil Test participants’ ability to identify phishing web sites before and after training up to 15 min –10 web sites before training, 10 after, randomized order Three conditions: –Web-based phishing education –Printed tutorial of our materials –Anti-phishing Phil 14 participants in each condition –Screened out security experts –Younger, college students
Results No statistically significant difference in false negatives among the three groups –Actually a phish, but participant thinks it’s not –Unsure why, preparing for a larger online study Though game group had fewest false positives Press release this week, just got 800 new users –Banks, non-profits, consulting firms, Air Force, ISPs
Outline Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm Do people see, understand, and believe web browser warnings?
Screenshots Internet Explorer – Passive Warning
Screenshots Internet Explorer – Active Block
Screenshots Mozilla FireFox – Active Block
How Effective are these Warnings? Tested four conditions –FireFox Active Block –IE Active Block –IE Passive Warning –Control (no warnings or blocks) “Shopping Study” –Setup some fake phishing pages and added to blacklists –Users were phished after purchases –Real accounts and personal information –Spoofing eBay and Amazon (2 phish/user) –We observed them interact with the warnings
How Effective are these Warnings?
Discussion of Phish Warnings Nearly everyone will fall for highly contextual phish Passive IE warning failed for many reasons –Didn’t interrupt the main task –Slow to appear (up to 5 seconds) –Not clear what the right action was –Looked too much like other ignorable warnings (habituation) –Bug in implementation, any keystroke dismisses
Screenshots Internet Explorer – Passive Warning
Discussion of Phish Warnings Active IE warnings –Most saw but did not believe it “Since it gave me the option of still proceeding to the website, I figured it couldn’t be that bad” –Some element of habituation (looks like other warnings) –Saw two pathological cases
Screenshots Internet Explorer – Active Block
A Science of Warnings See the warning? Understand? Believe it? Motivated? Planning on refining this model for computer warnings
Outline Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm Can we automatically detect phish s?
PILFER Anti-Phishing Filter Philosophy: automate where possible, support where necessary Goal: Create filter that detects phishing s –Spam filters well-explored, but how good for phishing? –Can we create a custom filter for phishing? I. Fette, N. Sadeh, A. Tomasic. Learning to Detect Phishing s. In W W W 2007.
PILFER Anti-Phishing Filter Heuristics combined in SVM –IP addresses in link ( –Age of linked-to domains (younger domains likely phishing) –Non-matching URLs (ex. most links point to PayPal) –“Click here to restore your account” –HTML –Number of links –Number of domain names in links –Number of dots in URLs ( –JavaScript –SpamAssassin rating
PILFER Evaluation Ham corpora from SpamAssassin (2002 and 2003) –6950 good s Phishingcorpus –860 phishing s
PILFER Evaluation
PILFER now implemented as SpamAssassin filter Alas, Ian has left for Google
Outline Human side –Interviews to understand decision-making –PhishGuru embedded training –Anti-Phishing Phil game –Understanding effectiveness of browser warnings Computer side –PILFER anti-phishing filter –CANTINA web anti-phishing algorithm How good is phish detection for web sites? Can we do better?
Lots of Phish Detection Algorithms Dozens of anti-phishing toolbars offered –Built into security software suites –Offered by ISPs –Free downloads –132 on download.com –Built into latest version of popular web browsers
Lots of Phish Detection Algorithms Dozens of anti-phishing toolbars offered –Built into security software suites –Offered by ISPs –Free downloads –132 on download.com –Built into latest version of popular web browsers But how well do they detect phish? –Short answer: still room for improvement
Testing the Toolbars November 2006: Automated evaluation of 10 toolbars –Used phishtank.com and APWG as source of phishing URLs –Evaluated 100 phish and 510 legitimate sites Y. Zhang, S. Egelman, L. Cranor, J. Hong. Phinding Phish: An Evaluation of Anti-Phishing Toolbars. NDSS 2006.
Testbed System Architecture
Results 38% false positives 1% false positives PhishTank
APWG
Results Only one toolbar >90% accuracy (but high false positives) Several catch 70-85% of phish with few false positives
Results Only one toolbar >90% accuracy (but high false positives) Several catch 70-85% of phish with few false positives Can we do better? –Can we use search engines to help find phish? Y. Zhang, J. Hong, L. Cranor. CANTINA: A Content- Based Approach to Detecting Phishing Web Sites. In W W W 2007.
Robust Hyperlinks Developed by Phelps and Wilensky to solve “404 not found” problem Key idea was to add a lexical signature to URLs that could be fed to a search engine if URL failed –Ex. How to generate signature? –Found that TF-IDF was fairly effective Informal evaluation found five words was sufficient for most web pages
Adapting TF-IDF for Anti-Phishing Can same basic approach be used for anti-phishing? –Scammers often directly copy web pages –With Google search engine, fake should have low page rank FakeReal
How CANTINA Works Given a web page, calculate TF-IDF score for each word in that page Take five words with highest TF-IDF weights Feed these five words into a search engine (Google) If domain name of current web page is in top N search results, we consider it legitimate –N=30 worked well –No improvement by increasing N Later, added some heuristics to reduce false positives
Fake eBay, user, sign, help, forgot
Real eBay, user, sign, help, forgot
Evaluating CANTINA PhishTank
Summary Whirlwind tour of our work on anti-phishing –Human side: how people make decisions, training, UIs –Computer side: better algorithms for detecting phish More info about our work at cups.cs.cmu.edu
Opportunities! Usable Privacy and Security class –Spring 2008, taught by Lorrie Cranor APWG eCrime Research Summit –Oct 4-5, here at CMU ( CUPS group – Trust group jobs –Design of interventions –Help implement PhishGuru for larger scale
Acknowledgments Alessandro Acquisti Lorrie Cranor Sven Dietrich Julie Downs Mandy Holbrook Norman Sadeh Anthony Tomasic Umut Topkara Supported by NSF, ARO, CyLab, Portugal Telecom Serge Egelman Ian Fette Ponnurangam Kumaraguru Bryant Magnien Elizabeth Nunge Yong Rhee Steve Sheng Yue Zhang
C MU U sable P rivacy and S ecurity Laboratory
Embedded Training Results
Is it legitimate Our label YesNo YesTrue positiveFalse positive NoFalse negativeTrue negative
Minimal Knowledge of Lock Icon “I think that it means secured, it symbolizes some kind of security, somehow.” 85% of participants were aware of lock icon Only 40% of those knew that it was supposed to be in the browser chrome Only 35% had noticed https, and many of those did not know what it meant