By Topic

Information Forensics and Security (WIFS), 2012 IEEE International Workshop on

Date 2-5 Dec. 2012

Filter Results

Displaying Results 1 - 25 of 56
  • [Front cover]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (349 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | PDF file iconPDF (724 KB)  
    Freely Available from IEEE
  • Author index

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | PDF file iconPDF (719 KB)  
    Freely Available from IEEE
  • Preface

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (339 KB)  
    Freely Available from IEEE
  • Organizing committee

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | PDF file iconPDF (582 KB)  
    Freely Available from IEEE
  • Sponsors

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (828 KB)  
    Freely Available from IEEE
  • WIFS'12 Keynotes [3 abstracts]

    Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB)  

    Provides an abstract for each of the three keynote presentations. They are: "Adversary-aware signal processing" by Prof. Dr. Mauro Barni (University of Siena, Italy); "Playing hide and seek on-line: anonymous communication, traffic analysis and censorship" by Dr. George Danezis (Microsoft Research Cambridge, UK); and Issues, Controversies and Advancements in Forensic Speaker Recognition - IEEE Biometrics Council Distinguished Lecturer Talk" by Prof. Dr. James L. Wayman (Office of Graduate Studies and Research, San Jose State University, San Jose, California, USA). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • WIFS'12 Demos [8 abstracts]

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | PDF file iconPDF (1049 KB)  
    Freely Available from IEEE
  • Detecting fingerprint distortion from a single image

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2714 KB) |  | HTML iconHTML  

    Elastic distortion of friction ridge skin is one of the major challenges in fingerprint matching. Since existing fingerprint matching systems cannot match seriously distorted fingerprints, criminals may purposely distort their fingerprints to evade identification. Existing distortion detection techniques require availability of specialized hardware or fingerprint video, limiting their use in real applications. In this paper we conduct a study on fingerprint distortion and develop an algorithm to detect fingerprint distortion from a single image which is captured using traditional fingerprint sensing techniques. The detector is based on analyzing ridge period and orientation information. Promising results are obtained on a public domain fingerprint database containing distorted fingerprints. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novel fingerprint aging features using binary pixel sub-tendencies: A comparison of contactless CLSM and CWL sensors

    Page(s): 7 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (944 KB) |  | HTML iconHTML  

    Age determination of latent fingerprints from crime scenes is an open challenge to forensic experts since several decades. In recent publications it was shown that a feature called binary pixel in combination with a contactless and non-invasive Chromatic White Light (CWL) image sensor is able to distinguish between fingerprints younger as or older than five hours with an accuracy of about 70-80%. Such approach can be seen as a very promising first step, but needs to be improved (e.g. by a fusion with additional aging features) to reach error rates that would be acceptable in legal proceedings. In the scope of this paper, two novel aging features are introduced and evaluated as opposing sub-tendencies of the classical binary pixel feature. Furthermore, Confocal Laser Scanning Microscopy (CLSM) is firstly applied to fingerprint aging evaluations. In our experiments, 200 fingerprint time series (captured every hour for 24 hours) for each the novel CLSM as well as the classical CWL device (9600 fingerprint images in total) are evaluated and compared using the classical binary pixel feature as well as both novel sub-tendency features. We show that one of such new sub-tendencies performs very well for the CLSM device (90% of curves show a strong logarithmic aging behavior), while for the CWL sensor the classical binary pixel feature performs best (87% of curves showing a strong logarithmic aging behavior). The increased performance of such new feature can be seen as very suitable for complementing the classical CWL binary pixel aging feature in a future age estimation approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Facial landmark configuration for improved detection

    Page(s): 13 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1482 KB) |  | HTML iconHTML  

    In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches: (i) a multivariate conditional Gaussian-based model, and (ii) a MRF-based formulation with higher-order potentials. We evaluated the performance of our proposed methods using several state-of-the-art detectors, and consistently obtained improved performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-stage appearance-based re-identification of humans in low-resolution videos

    Page(s): 19 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1361 KB) |  | HTML iconHTML  

    The objective of human re-identification is to recognize a specific individual on different locations and to determine whether an individual has already appeared. This is especially in multi-camera networks with non-overlapping fields of view of interest. However, this is still an unsolved computer vision task due to several challenges, e.g. significant changes of appearance of humans as well as different illumination, camera parameters etc. In addition, for instance, in surveillance scenarios only low-resolution videos are usually available, so that biometric approaches may not be applied. This paper presents a whole-body appearance-based human re-identification approach for low-resolution videos. The method is divided in two stages: first, an appearance model is computed from several images of an individual and pairwise compared to each other. The model is based on means of covariance descriptors determined by spectral clustering techniques. In the second stage, the result is refined by learning the appearance manifolds of the best matches. The proposed approach is tested on a multi-camera data set of a typical surveillance scenario and compared to a color histogram based method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Biometric template protection using turbo codes and modulation constellations

    Page(s): 25 - 30
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1282 KB) |  | HTML iconHTML  

    In this paper we propose a general biometric cryptosystem framework inspired by the code-offset sketch. Specifically, the properties of digital modulation and turbo codes with soft-decoding are exploited to design a template protection system able to guarantee high performance in terms of both verification rates and security, also when dealing with biometrics characterized by a high intra-class variability. The effectiveness of the presented approach is evaluated by its application as case study to on-line signature recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Can a “poor” verification system be a “good” identification system? A preliminary study

    Page(s): 31 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1430 KB) |  | HTML iconHTML  

    The matching accuracy of a biometric system is typically quantified through measures such as the False Match Rate (FMR), False Non-match Rate (FNMR), Equal Error Rate (EER), Receiver Operating Characteristic (ROC) curve and Cumulative Match Characteristic (CMC) curve. In this work, we analyze the relationship between the ROC and CMC curves, which are two measures commonly used to describe the performance of verification and identification systems, respectively. We establish that it is possible for a biometric system to exhibit “good” verification performance and “poor” identification performance (and vice versa) by demonstrating the conditions required to produce such outcomes. Experimental analysis using synthetically generated match scores confirms our hypothesis that the ROC or CMC alone cannot completely characterize biometric system performance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Machine learning attacks on 65nm Arbiter PUFs: Accurate modeling poses strict bounds on usability

    Page(s): 37 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1277 KB) |  | HTML iconHTML  

    Arbiter Physically Unclonable Functions (PUFs) have been proposed as efficient hardware security primitives for generating device-unique authentication responses and cryptographic keys. However, the assumed possibility of modeling their underlying challenge-response behavior causes uncertainty about their actual applicability. In this work, we apply well-known machine learning techniques on challenge-response pairs (CRPs) from 64-stage Arbiter PUFs realized in 65nm CMOS, in order to evaluate the effectiveness of such modeling attacks on a modern silicon implementation. We show that a 90%-accurate model can be built from a training set of merely 500 CRPs, and that 5000 CRPs are sufficient to perfectly model the PUFs. To study the implications of these attacks, there is need for a new methodology to assess the security of PUFs suffering from modeling. We propose such a methodology and apply it to our machine learning results, yielding strict bounds on the usability of Arbiter PUFs. We conclude that plain 64-stage Arbiter PUFs are not secure for challenge-response authentication, and the number of extractable secret key bits is limited to at most 600. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Towards reproducible results in authentication based on physical non-cloneable functions: The forensic authentication microstructure optical set (FAMOS)

    Page(s): 43 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2017 KB) |  | HTML iconHTML  

    Nowadays, the field of physical object security based on surface microstructures lacks common and shared data for the development, testing and fair benchmarking of new identification and authentication technologies. To our knowledge, most published results are based on proprietary data that also often lacks the necessary size for statistically significant results and conclusions. Therefore, in this paper, we introduce the first publicly available documented database for the investigation of physical object authentication based on non-cloneable surface microstructure images. We have built an automatic system suitable for massive acquisition of microstructure images from flat surfaces under different light conditions and with different cameras. The samples are acquired several times, and resulting images are aligned, labelled and online available to the public for further investigation and benchmarking of new methods. In this paper, we present the statistical properties for the images originating from 5000 unique carton packages acquired 6 times each with two different cameras. Furthermore, we derive statistical authentication frameworks for the original, the random projected and binarized domains presented together with all empirical results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improving the DGK comparison protocol

    Page(s): 49 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1384 KB) |  | HTML iconHTML  

    When processing signals in the encrypted domain, homomorphic encryption can be used to enable linear operations on encrypted data. Comparison of encrypted data however requires an additional protocol between the parties and will be relatively expensive. A well-known and frequently used comparison protocol is by Damgard, Geisler and Kroigaard. We present two ways of improving this comparison protocol. Firstly, we reduce the computational effort of one party by roughly 50%. Secondly, we show how to achieve perfect security towards the other party without additional costs, whereas the original version with encrypted inputs only achieved statistical security. An additional advantage is that larger inputs are allowed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • General function evaluation in a STPC setting via piecewise linear approximation

    Page(s): 55 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1344 KB) |  | HTML iconHTML  

    While in theory any computable functions can be evaluated in a Secure Two Party Computation (STPC) framework, practical applications are often limited for complexity reasons and by the kind of operations that the available cryptographic tools permit. In this paper we propose an algorithm that, given a function f() and an interval belonging to its domain, produces a piecewise linear approximation f() that can be easily implemented in a STPC setting. Two different implementations are proposed: the first one relies completely on Garbled Circuit (GC) theory, while the second one exploits a hybrid construction where GC and Homomorphic Encryption (HE) are used together. We show that from a communication complexity perspective the full-GC implementation is preferable when the input and output variables are represented with a small number of bits, otherwise the hybrid solution is preferable. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for privacy preserving statistical analysis on distributed databases

    Page(s): 61 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1003 KB) |  | HTML iconHTML  

    Alice and Bob are mutually untrusting curators who possess separate databases containing information about a set of respondents. This data is to be sanitized and published to enable accurate statistical analysis, while retaining the privacy of the individual respondents in the databases. Further, an adversary who looks at the published data must not even be able to compute statistical measures on it. Only an authorized researcher should be able to compute marginal and joint statistics. This work is an attempt toward providing a theoretical formulation of privacy and utility for problems of this type. Privacy of the individual respondents is formulated using ϵ-differential privacy. Privacy of the marginal and joint statistics on the distributed databases is formulated using a new model called δ-distributional ϵ-differential privacy. Finally, a constructive scheme based on randomized response is presented as an example mechanism that satisfies the formulated privacy requirements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling and analysis of Electric Network Frequency signal for timestamp verification

    Page(s): 67 - 72
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1397 KB) |  | HTML iconHTML  

    Electric Network Frequency (ENF) fluctuations based forensic analysis is recently proposed for time-of-recording estimation, timestamp verification, and clip insertion/deletion forgery detection in multimedia recordings. Due to the load control mechanism of the electric grid, ENF fluctuations exhibit pseudo-periodic behavior and generally require a long duration of recording for forensic analysis. In this paper, a statistical study of the ENF signal is conducted to model it using an autoregressive process. The proposed model is used to understand the effect of the ENF signal duration and signal-to-noise ratio on the detection performance of a timestamp verification system under a hypothesis detection framework. Based on the proposed model, a decorrelation based approach is studied to match the ENF signals for timestamp verification. The proposed approach requires a shorter duration of the ENF signal to achieve the same detection performance as without decorrelation. Experiments are conducted on audio data to demonstrate an improvement in the detection performance of the proposed approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Telephone handset identification by feature selection and sparse representations

    Page(s): 73 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1607 KB) |  | HTML iconHTML  

    Speech signals convey information not only for the speakers' identity and the spoken language, but also for the acquisition devices used during their recording. Therefore, it is reasonable to perform acquisition device identification by analyzing the recorded speech signal. To this end, the random spectral features (RSFs) and the labeled spectral features (LSFs) are proposed as intrinsic fingerprints suitable for device identification. The RSFs and the LSFs are extracted by applying unsupervised and supervised feature selection to the mean spectrogram of each speech signal, respectively. State-of-the-art identification accuracy of 97.58% has been obtained by employing LSFs on a set of 8 telephone handsets, from Lincoln-Labs Handset Database (LLHDB). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Privacy-preserving architecture for forensic image recognition

    Page(s): 79 - 84
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1397 KB) |  | HTML iconHTML  

    Forensic image recognition is an important tool in many areas of law enforcement where an agency wants to prosecute possessors of illegal images. The recognition of illegal images that might have undergone human imperceptible changes (e.g., a JPEG-recompression) is commonly done by computing a perceptual image hash function of a given image and then matching this hash with perceptual hash values in a database of previously collected illegal images. To prevent privacy violation, agencies should only learn about images that have been reliably detected as illegal and nothing else. In this work, we argue that the prevalent presence of separate departments in such agencies can be used to enforce the need-to-know principle by separating duties among them. This enables us to construct the first practically efficient architecture to perform forensic image recognition in a privacy-preserving manner. By deriving unique cryptographic keys directly from the images, we can encrypt all sensitive data and ensure that only illegal images can be recovered by the law enforcement agency while all other information remains protected. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sequence detection of overlapping latent fingerprints using a short-term aging feature

    Page(s): 85 - 90
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1980 KB) |  | HTML iconHTML  

    This paper presents a novel approach for sequence detection of overlapping latent fingerprints for crime scene forensics. The approach involves a contactless and nondestructive acquisition of untreated fingerprints by using a Chromatic White Light (CWL) sensor. Based on 40 time series with 1160 samples, our approach shows how an aging feature called Binary Pixel for measuring the short-term decay of fingerprint samples can be used in combination with overlapping fingerprint separation methods for sequence detection. This allows differentiating which latent fingerprint was placed first and which later and thus provides contextual information for criminal investigations. Our experiments show promising results with a detection accuracy of at least 70%, regardless of the initial age of both the older and newer fingerprint. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantic based DNS forensics

    Page(s): 91 - 96
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1766 KB) |  | HTML iconHTML  

    In network level forensics, Domain Name Service (DNS) is a rich source of information. This paper describes a new approach to mine DNS data for forensic purposes. We propose a new technique that leverages semantic and natural language processing tools in order to analyze large volumes of DNS data. The main research novelty consists in detecting malicious and dangerous domain names by evaluating the semantic similarity with already known names. This process can provide valuable information for reconstructing network and user activities. We show the efficiency of the method on experimental real datasets gathered from a national passive DNS system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fingerprinting a flow of messages to an anonymous server

    Page(s): 97 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1254 KB) |  | HTML iconHTML  

    We present an attack to locate hidden servers in anonymous common networks. The attack is based on correlating the flow of messages that arrives to a certain server with the flow that is created by the attacker client. The fingerprint is constructed by sending requests, each request determines one interval. To improve the performance a prediction of the time of arrival is done for each request. We propose an optimal detector to decide whether the flow is fingerprinted, based on the Neyman-Pearson lemma. The usefulness of our algorithm is shown for the case of locating a Tor Hidden Service (HS), where we analytically determine the parameters that yield a fixed false positive probability and compute the corresponding detection probability. Finally, we empirically validate our results with a simulator and with a real implementation on the live Tor network. Results show that our algorithm outperforms any other flow watermarking scheme. Our design also yields a small detectability. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.