IMAGINATION: A Robust Image-based CAPTCHA Generation System Ritendra Datta, Jia Li, and James Z. Wang The Pennsylvania State University – University Park.

Slides:



Advertisements
Similar presentations
CAPTCHA: Using Hard AI Problems for Security 12 Jun 2007 Ohad Barak (a.k.a. jo) Luis Von Ahn, EuroCrypt 2003.
Advertisements

CrowdSearch: Exploiting Crowds for Accurate Real-time Image Search on Mobile Phones Original work by Yan, Kumar & Ganesan Presented by Shibo Li & Jian.
A Distributed Security Framework for Heterogeneous Wireless Sensor Networks Presented by Drew Wichmann Paper by Himali Saxena, Chunyu Ai, Marco Valero,
VisualRank: Applying PageRank to Large-Scale Image Search Yushi Jing, Member, IEEE, and Shumeet Baluja, Member, IEEE.
CAPTCHA Completely Automated Public Turing test to tell Computers and Humans Apart A Computer Program that can generate and grade test that: Most Humans.
1 Building a Dictionary of Image Fragments Zicheng Liao Ali Farhadi Yang Wang Ian Endres David Forsyth Department of Computer Science, University of Illinois.
A Low-cost Attack on a Microsoft CAPTCHA Yan Qiang,
CAPTCHA Presented by: Sari Louis SPAM Group: Marc Gagnon, Sari Louis, Steve White University of Illinois Spring 2006.
AN IMPROVED AUDIO Jenn Tam Computer Science Dept. Carnegie Mellon University SOAPS 2008, Pittsburgh, PA.
Breaking an Animated CAPTCHA Scheme
CAPTCHA Presented By Sayani Chandra (Roll )
Advanced Computer Vision Introduction Goal and objectives To introduce the fundamental problems of computer vision. To introduce the main concepts and.
Watermarking in WSNs Anuj Nagar CS 590. Introduction WSNs provide computational and Internet interfaces to the physical world. They also pose a number.
Content-based Image Retrieval CE 264 Xiaoguang Feng March 14, 2002 Based on: J. Huang. Color-Spatial Image Indexing and Applications. Ph.D thesis, Cornell.
A Study of Approaches for Object Recognition
Jeff Yan School of Computing Science Newcastle University, UK (Joint work with Ahmad Salah El Ahmad) Usability of CAPTCHAs Or “usability issues in CAPTCHA.
CMSC 414 Computer and Network Security Lecture 21 Jonathan Katz.
A Poisoning-Resilient TCP Stack Amit Mondal Aleksandar Kuzmanovic Northwestern University
Providing Trusted Paths Using Untrusted Components Andre L. M. dos Santos Georgia Institute of Technology
Building Robust and Automatic Authentication Systems with Activity- Based Personal Questions Mentor: Danfeng Yao Anitra Babic Chestnut Hill College Computer.
Telling Humans and Computers Apart (Automatically) Or How Lazy Cryptographers do AI Luis von Ahn The Aladdin Center Carnegie Mellon University.
CAPTCHA Prabhakar Verma “08MC30”.
1 CAPTCHA Challenges for Massively Multiplayer Online Games 2010 International Conference on Cyberworlds Authors: Yang-Wai Chow, Willy Susilo, Hua-Yu Zhou.
Computer Vision Group University of California Berkeley Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA Greg Mori and Jitendra Malik.
Genetically optimized face image CAPTCHA
Human Computation CSC4170 Web Intelligence and Social Computing Tutorial 7 Tutor: Tom Chao Zhou
Authentication for Humans Rachna Dhamija SIMS, UC Berkeley DIMACS Workshop on Usable Privacy and Security Software July 7, 2004.
1 Securing Passwords Against Dictionary Attacks Base on an article by Benny Pinkas & Tomas Sander 2002 Presented by Tomer Conforti.
Internet Quarantine: Requirements for Containing Self-Propagating Code David Moore et. al. University of California, San Diego.
CrowdSearch: Exploiting Crowds for Accurate Real-Time Image Search on Mobile Phones Original work by Yan, Kumar & Ganesan Presented by Tim Calloway.
Evolving Multi-modal Behavior in NPCs Jacob Schrum – Risto Miikkulainen –
CAPTCHA 1 Are you Human? (Sorry, I had to ask). CAPTCHA 2 Agenda What is CAPTCHA? Types of CAPTCHA Where to use CAPTCHAs? Guidelines when making a CAPTCHA.
Part 2  Access Control 1 CAPTCHA Part 2  Access Control 2 Turing Test Proposed by Alan Turing in 1950 Human asks questions to another human and a computer,
Protecting Web 2.0 Services from Botnet Exploitations Cybercrime and Trustworthy Computing Workshop (CTC), 2010 Second Nguyen H Vo, Josef Pieprzyk Department.
Web Policy Zeitgeist Panel SWPW 2005 – Galway, Ireland Piero Bonatti, November 7th, 2005.
Network Aware Resource Allocation in Distributed Clouds.
Ideas Session Willer Travassos, Jan. 24th. GWAP Games with a purpose (GWAP) uses the computational power of humans to perform tasks that computers are.
Captcha Breaker 技巧很強壯的大叔隊. Workflow Outline Segmentation – Human Visual System Segmentation – Color Filling Segmentation – Distortion Estimation Optical.
A Dynamic Packet Stamping Methodology for DDoS Defense Project Presentation by Maitreya Natu, Kireeti Valicherla, Namratha Hundigopal CISC 859 University.
Preventing Automated Use of STMP Reservation System Using CAPTCHA.
Aspect-Oriented Requirements Engineering David Schaefer, Joao Araujo, Isabel Brito, Awais Rashid, Claudia Mesquita.
REVISITING DEFENSES AGAINST LARGE SCALE ONLINE PASSWORD GUESSING ATTACKS Mansour Alsaleh,Mohammad Mannan and P.C van Oorschot.
Presented By: Abirami Poonkundran Authors: Jeff Yan, Ahmad El Ahmad.
By Gianluca Stringhini, Christopher Kruegel and Giovanni Vigna Presented By Awrad Mohammed Ali 1.
Jawaharlal Nehru National College of Engineering, Shimoga – Department of Computer Science & Engineering Technical Seminar on, Under the guidance.
Optimal Resource Allocation for Protecting System Availability against Random Cyber Attack International Conference Computer Research and Development(ICCRD),
Securing Passwords Against Dictionary Attacks Presented By Chad Frommeyer.
Search Worms, ACM Workshop on Recurring Malcode (WORM) 2006 N Provos, J McClain, K Wang Dhruv Sharma
Effective Automatic Image Annotation Via A Coherent Language Model and Active Learning Rong Jin, Joyce Y. Chai Michigan State University Luo Si Carnegie.
Designing Human Friendly Human Interaction Proofs (HIPs) Kumar Chellapilla, Kevin Larson, Patrice Simard and Mary Czerwinski Microsoft Research Presented.
Socialbots and its implication On ONLINE SOCIAL Networks Md Abdul Alim, Xiang Li and Tianyi Pan Group 18.
Iasonas Polakis, Panagiotis Ilia, Federico Maggi, Marco Lancini, Georgios Kontaxis, Stefano Zanero, Sotiris Ioannidis, and Angelos D. Keromytis. In Proceedings.
YES Has student annotated work, identifying errors and highlighting areas where feedback is required? NO Return work to student unmarked and insist that.
Speaker Min-Koo Kang March 26, 2013 Depth Enhancement Technique by Sensor Fusion: MRF-based approach.
CAP Malware and Software Vulnerability Analysis Term Project Proposal - Spring 2009 Professor: Dr. Zou Team members: Andrew Mantel & Peter Matthews.
Peter Matthews, Cliff C. Zou University of Central Florida AsiaCCS 2010.
By: Steven Baker.  What is a CAPTCHA?  History of CAPTCHA  Applications of CAPTCHAs  Accessibility  Examples of CAPTCHAs  reCAPTCHA  Vulnerabilities.
Separating man from machine since 2000….. ?. Agenda  Definition  History  Need  Types  Constructing CAPTCHAs  Breaking CAPTCHAs  Applications 
CAPTCHA What humans can do, But computers can not.
Usability of CAPTCHAs Or usability issues in CAPTCHA design Authors: Jeff Yan and Ahmad Salah El Ahmad Presented By: Kim Giglia CSC /19/2008.
SUBMITTED TO:-SUBMITTED BY:- Ms.Kavita KhannaShruty Ahuja H.O.D(CSE DEPARTMENT)02/MT/10 PDM,BAHADURGARHCE(2 ND SEM)
CAPTCHA Presented by: Md.R ahim 08B21A Agenda Definition Background Motivation Applications Types of CAPTCHAs Breaking CAPTCHAs Proposed Approach.
SANDEEP MEHTA (ECE, IV Year). CAPTCHA Completely Automated Public Turing test to tell Computers and Humans Apart Invented at CMU by Luis von Ahn, Manuel.
3.6 Fundamentals of cyber security
Are you Human?.
Web Programming Week 11 Old Dominion University
Content-based Image Retrieval
Advanced Techniques for Automatic Web Filtering
A novel probabilistic language-based CAPTCHA system
Information Theoretical Analysis of Digital Watermarking
Presentation transcript:

IMAGINATION: A Robust Image-based CAPTCHA Generation System Ritendra Datta, Jia Li, and James Z. Wang The Pennsylvania State University – University Park ACM International Conference on Multimedia, November 2005

What are CAPTCHAs 1,2 ? Completely Automated Public Test to Tell Computers and Humans Apart. Web-based protection mechanisms Only humans allowed to perform certain tasks`  Opening accounts  Voting on-line, etc. Prevent automated attacks by bots  To avoid eating up resources  To avoid biasing results, etc. Most current systems - text-based. Text-based CAPTCHAs 1.L. von Ahn et al., CACM, The CAPTCHA Project –

Why image-based CAPTCHAs ? Computer vision techniques 1,2,3 have broken text-based CAPTCHAs  Over 90% accuracy  Makes these systems vulnerable Solution  More noise – harder for humans too  Natural image based CAPTCHAs Present an image to the user  User labels content Hard to attack  Image recognition is a hard problem  Hence more secure CAPTCHAs ! 1.G. Mori et al., CVPR, A. Thayananthan et al., CVPR, G. Moy et al., CVPR, Image-based CAPTCHAs (Courtesy: The Captcha Project, CMU)

What’s the problem ? CBIR (e.g. SIMPLIcity) and automated annotation systems (e.g. ALIP) may attack Solution: Generate CAPTCHA images that  Humans can easily label  Automated systems fail in most cases How  Use systematic distortions on images. Dithering, noise, quantizing etc.  Maintain low perceptual degradation  Test using state-of-the-art automated systems  Optimize attack rate & perceptual quality  Generate word choices systematically to reduce ambiguity and attack chance SIMPLIcity and ALIP (Pictures courtesy Corel)

The IMAGINATION System Image Generation for Internet Authentication. Exploits the difference between human perception and current level of machine perception. Generates a CAPTCHA based on a hard AI problem. Breaking IMAGINATION, though highly unlikely, would in turn advance the state-of-the-art in AI. Uses a two-phase click-and- annotate process to achieve very low chance of attack. Click Phase – Select center of an image Annotate Phase – Select best label from list

The IMAGINATION System: Architecture

Composite Image Generation Composite image generation by re-partitioning and dithering using different randomly chosen base colors

Composite Distortion Selection How to smartly choose distortions that can be applied to the images ? Use state-of-the-art CBIR/related systems that can be potential attack weapons Enforce probabilistic constraints on what is a good distortion  Make some realistic assumptions  Generate many distortions  Choose a subset that satisfies these constraints  Include in the IMAGINATION system A tiger image distorted by four acceptable composite distortions

Composite Distortions: Probabilistic Constraints An image distortion is considered acceptable, if probabilistically, potential attack algorithms are unable to significantly reduce the uncertainty associated with the labeling of those images

Composite Distortions in IMAGINATION Schematic view of the four composite distortions satisfying the probabilistic constraints and hence chosen for the IMAGINATION system

Word Choice Generation User choose instead of types:  Avoid spelling mistakes, polysemy etc.  More user-friendly (critical)  But leads to higher attack chance ! Three issues with choice list generation  Ambiguity (e.g. Dog and Wolf)  Attack using word choices themselves (Odd-one-out)  Multiple valid labels Solution  Use the WordNet ontology  Solve heuristically by constructing a word hyper-tetrahedron W1W1 W2W2 W4W4 W3W3 d 1,3 d 2,4, d 1,4 d 1,3 d 1,2 d 3,4 A word hyper-tetrahedron (K=4) W k = word choice, k = {1, …, K} d i,j = WordNet distance between W i & W j Constraint: d i,j ≈ δ, for all (i,j)

Conclusions New form of CAPTCHA  Likely to be more robust against attacks Some issues  Need more rigorous testing against many attack scenarios  User-friendliness is critical – needs large-scale testing Given these issues are somewhat addressed  Promise of a more secure Internet  Web servers more reliable  Potential for commercialization