Ivo Shterev - Academia.edu (original) (raw)

Papers by Ivo Shterev

Research paper thumbnail of Maximum likelihood amplitude scale estimation for quantization-based watermarking in the presence of Dither

Proceedings of Spie the International Society For Optical Engineering, 2005

Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves th... more Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. The existence of good high dimensional lattices that can be efficiently implemented and incorporated into watermarking structures, made quantization-based watermarking schemes of practical interest. Because of the structure of the lattices, watermarking schemes making use of them are vulnerable to non-additive operations, like amplitude scaling in combination with additive noise. In this paper, we propose a secure Maximum Likelihood (ML) estimation technique for amplitude scaling factors using subtractive dither. The dither has mainly security purposes and is assumed to be known to the watermark encoder and decoder. We derive the probability density function (PDF) models of the watermarked and attacked data in the presence of subtractive dither. The derivation of these models follows the lines of reference 5, where we derived the PDF models in the absence of dither. We derive conditions for the dither sequence statistics such that a given security level is achieved using the error probability of the watermarking system as objective function. Based on these conditions we are able to make approximations to the PDF models that are used in the ML estimation procedure. Finally, experiments are performed with real audio and speech signals showing the good performance of the proposed estimation technique under realistic conditions.

Research paper thumbnail of Statistical amplitude scale estimation for quantization-based watermarking

Security, Steganography, and Watermarking of Multimedia Contents, 2004

Quantization-based watermarking schemes are vulnerable to amplitude scaling. Therefore the scalin... more Quantization-based watermarking schemes are vulnerable to amplitude scaling. Therefore the scaling factor has to be accounted for either at the encoder, or at the decoder, prior to watermark decoding. In this paper we derive the marginal probability density model for the watermarked and attacked data, when the attack channel consists of amplitude scaling followed by additive noise. The encoder is

Research paper thumbnail of Quantization-based watermarking: methods for amplitude scale estimation, security, and linear filtering invariance

Research paper thumbnail of <title>Maximum likelihood amplitude scale estimation for quantization-based watermarking in the presence of dither</title>

Security, Steganography, and Watermarking of Multimedia Contents VII, 2005

Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves th... more Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. The existence of good high dimensional lattices that can be efficiently implemented and incorporated into watermarking structures, made quantization-based watermarking schemes of practical interest. Because of the structure of the lattices, watermarking schemes making use of them are vulnerable to non-additive operations, like amplitude scaling in combination with additive noise. In this paper, we propose a secure Maximum Likelihood (ML) estimation technique for amplitude scaling factors using subtractive dither. The dither has mainly security purposes and is assumed to be known to the watermark encoder and decoder. We derive the probability density function (PDF) models of the watermarked and attacked data in the presence of subtractive dither. The derivation of these models follows the lines of reference 5, where we derived the PDF models in the absence of dither. We derive conditions for the dither sequence statistics such that a given security level is achieved using the error probability of the watermarking system as objective function. Based on these conditions we are able to make approximations to the PDF models that are used in the ML estimation procedure. Finally, experiments are performed with real audio and speech signals showing the good performance of the proposed estimation technique under realistic conditions.

Research paper thumbnail of <title>Scale estimation in two-band filter attacks on QIM watermarks</title>

Security, Steganography, and Watermarking of Multimedia Contents VIII, 2006

This paper presents a scheme for estimating two-band amplitude scale attack within a quantization... more This paper presents a scheme for estimating two-band amplitude scale attack within a quantization-based watermarking context. Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. Unfortunately, Quantization-based watermarking schemes are not robust against Linear Time Invariant (LTI) filtering attacks. We concentrate on a multi-band amplitude scaling attack that modifies

Research paper thumbnail of <title>Statistical amplitude scale estimation for quantization-based watermarking</title>

Security, Steganography, and Watermarking of Multimedia Contents VI, 2004

Research paper thumbnail of Estimation of attacker's scale and noise variance for qim-dc watermark embedding

2004 International Conference on Image Processing, 2004. ICIP '04., 2004

... 56 paper, wc refrain from explicitly modeling this effect, but take the dithering of the quan... more ... 56 paper, wc refrain from explicitly modeling this effect, but take the dithering of the quantizers into account ... tings have been used to benchmark the estimation proce-dure ... following table list our current results based on synthetic (Gaussian) data, with = 0.91, watermark-to-signal ...

Research paper thumbnail of Amplitude Scale Estimation for Quantization-Based Watermarking

IEEE Transactions on Signal Processing, 2000

In this paper we propose a maximum likelihood technique to combat amplitude scaling attacks withi... more In this paper we propose a maximum likelihood technique to combat amplitude scaling attacks within a quantizationbased watermarking context. We concentrate on operations that are common in many applications and at the same time devastating to this class of watermarking schemes, namely, amplitude scaling in combination with additive noise. First we derive the probability density function of the watermarked and attacked data in the absence of subtractive dither. Next we extend these models to incorporate subtractive dither in the encoder. The dither sequence is primarily used for security purposes, and the dither is assumed to be known also to the decoder. We design the dither signal statistics such that an attacker having no knowledge of the dither cannot decode the watermark. Using an approximation of the probability density function in the presence of subtractive dither, we derive a maximum likelihood procedure for estimating amplitude scaling factors. Experiments are performed with synthetic and real audio signals, showing the feasibility of the proposed approach under realistic conditions. Index Terms-Maximum likelihood estimation, probability of error, quantization, statistics, subtractive dither, watermarking.

Research paper thumbnail of permGPU : Using graphics processing units in RNA microarray association studies

Bmc Bioinformatics, 2010

Background: Many analyses of microarray association studies involve permutation, bootstrap resamp... more Background: Many analyses of microarray association studies involve permutation, bootstrap resampling and crossvalidation, that are ideally formulated as embarrassingly parallel computing problems. Given that these analyses are computationally intensive, scalable approaches that can take advantage of multi-core processor systems need to be developed.

Research paper thumbnail of Pharmacogenetic Discovery in CALGB (Alliance) 90401 and Mechanistic Validation of a VAC14 Polymorphism That Increases Risk of Docetaxel-Induced Neuropathy

Clinical cancer research : an official journal of the American Association for Cancer Research, Jan 3, 2016

Discovery of single nucleotide polymorphisms (SNPs) that predict a patient's risk of docetaxe... more Discovery of single nucleotide polymorphisms (SNPs) that predict a patient's risk of docetaxel-induced neuropathy would enable treatment individualization to maximize efficacy and avoid unnecessary toxicity. The objectives of this analysis were to discover SNPs associated with docetaxel-induced neuropathy and mechanistically validate these associations in preclinical models of drug-induced neuropathy. A genome-wide association study was conducted in metastatic castrate-resistant prostate cancer patients treated with docetaxel, prednisone and randomized to bevacizumab or placebo on CALGB 90401. SNPs were genotyped on the Illumina HumanHap610-Quad platform followed by rigorous quality control. The inference was conducted on the cumulative dose at occurrence of grade 3+ sensory neuropathy using a cause-specific hazard model that accounted for early treatment discontinuation. Genes with SNPs significantly associated with neuropathy were knocked down in cellular and mouse models of d...

Research paper thumbnail of Tumor markers of efficacy and resistance to cetuximab (C) treatment in metastatic colorectal cancer (mCRC): Results from CALGB 80203 (Alliance)

Asco Meeting Abstracts, May 20, 2013

Research paper thumbnail of A genome-wide association study (GWAS) of docetaxel-induced peripheral neuropathy in CALGB 90401 (Alliance)

Asco Meeting Abstracts, May 20, 2013

Research paper thumbnail of Gene Expression Markers of Efficacy and Resistance to Cetuximab Treatment in Metastatic Colorectal Cancer: Results from CALGB 80203 (Alliance)

Clinical Cancer Research, 2014

Purpose: Formalin-fixed, paraffin-embedded tumor samples from CALGB 80203 were analyzed for expre... more Purpose: Formalin-fixed, paraffin-embedded tumor samples from CALGB 80203 were analyzed for expression of EGFR axisrelated genes to identify prognostic or predictive biomarkers for cetuximab treatment.

Research paper thumbnail of Hierarchical kernel stick-breaking process for multi-task image analysis

Proceedings of the 25th international conference on Machine learning - ICML '08, 2008

The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the con... more The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the condition that patches (small blocks of pixels) that are spatially proximate are more likely to be associated with the same cluster (segment). The number of clusters is not set a priori and is inferred from the hierarchical Bayesian model. Further, KSBP is integrated with a shared Dirichlet process prior to simultaneously model multiple images, inferring their inter-relationships. This latter application may be useful for sorting and learning relationships between multiple images. The Bayesian inference algorithm is based on a hybrid of variational Bayesian analysis and local sampling. In addition to providing details on the model and associated inference framework, example results are presented for several image-analysis problems.

Research paper thumbnail of Integration of Cell Line and Clinical Trial Genome-Wide Analyses Supports a Polygenic Architecture of Paclitaxel-Induced Sensory Peripheral Neuropathy

Clinical Cancer Research, 2013

Purpose: We sought to show the relevance of a lymphoblastoid cell line (LCL) model in the discove... more Purpose: We sought to show the relevance of a lymphoblastoid cell line (LCL) model in the discovery of clinically relevant genetic variants affecting chemotherapeutic response by comparing LCL genome-wide association study (GWAS) results to clinical GWAS results.

Research paper thumbnail of permGPU: Using graphics processing units in RNA microarray association studies

BMC Bioinformatics, 2010

Background: Many analyses of microarray association studies involve permutation, bootstrap resamp... more Background: Many analyses of microarray association studies involve permutation, bootstrap resampling and crossvalidation, that are ideally formulated as embarrassingly parallel computing problems. Given that these analyses are computationally intensive, scalable approaches that can take advantage of multi-core processor systems need to be developed.

Research paper thumbnail of Security, Steganography, and Watermarking of Multimedia Contents VIII (Proceedings Volume)

The contribution of this paper is two-fold. First, we describe an improved version of a blind ste... more The contribution of this paper is two-fold. First, we describe an improved version of a blind steganalysis method previously proposed by Holotyak et al. and compare it to current state-of-the-art blind steganalyzers. The features for the blind classifier are calculated in the wavelet domain as higher-order absolute moments of the noise residual. This method clearly shows the benefit of calculating the features from the noise residual because it increases the features' sensitivity to embedding, which leads to improved detection results ...

Research paper thumbnail of Bayesian Watermark Attacks

This paper presents an application of statistical machine learning to the field of watermarking. ... more This paper presents an application of statistical machine learning to the field of watermarking. We propose a new attack model on additive spread-spectrum watermarking systems. The proposed attack is based on Bayesian statistics. We consider the scenario in which a watermark signal is repeatedly embedded in specific, possibly chosen based on a secret message bitstream, segments (signals) of the host data. The host signal can represent a patch of pixels from an image or a video frame. We propose a probabilistic model that infers the embedded message bitstream and watermark signal, directly from the watermarked data, without access to the decoder. We develop an efficient Markov chain Monte Carlo sampler for updating the model parameters from their conjugate full conditional posteriors. We also provide a variational Bayesian solution, which further increases the convergence speed of the algorithm. Experiments with synthetic and real image signals demonstrate that the attack model is able to correctly infer a large part of the message bitstream and obtain a very accurate estimate of the watermark signal.

Research paper thumbnail of Maximum likelihood amplitude scale estimation for quantization-based watermarking in the presence of Dither

Proceedings of Spie the International Society For Optical Engineering, 2005

Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves th... more Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. The existence of good high dimensional lattices that can be efficiently implemented and incorporated into watermarking structures, made quantization-based watermarking schemes of practical interest. Because of the structure of the lattices, watermarking schemes making use of them are vulnerable to non-additive operations, like amplitude scaling in combination with additive noise. In this paper, we propose a secure Maximum Likelihood (ML) estimation technique for amplitude scaling factors using subtractive dither. The dither has mainly security purposes and is assumed to be known to the watermark encoder and decoder. We derive the probability density function (PDF) models of the watermarked and attacked data in the presence of subtractive dither. The derivation of these models follows the lines of reference 5, where we derived the PDF models in the absence of dither. We derive conditions for the dither sequence statistics such that a given security level is achieved using the error probability of the watermarking system as objective function. Based on these conditions we are able to make approximations to the PDF models that are used in the ML estimation procedure. Finally, experiments are performed with real audio and speech signals showing the good performance of the proposed estimation technique under realistic conditions.

Research paper thumbnail of Statistical amplitude scale estimation for quantization-based watermarking

Security, Steganography, and Watermarking of Multimedia Contents, 2004

Quantization-based watermarking schemes are vulnerable to amplitude scaling. Therefore the scalin... more Quantization-based watermarking schemes are vulnerable to amplitude scaling. Therefore the scaling factor has to be accounted for either at the encoder, or at the decoder, prior to watermark decoding. In this paper we derive the marginal probability density model for the watermarked and attacked data, when the attack channel consists of amplitude scaling followed by additive noise. The encoder is

Research paper thumbnail of Quantization-based watermarking: methods for amplitude scale estimation, security, and linear filtering invariance

Research paper thumbnail of <title>Maximum likelihood amplitude scale estimation for quantization-based watermarking in the presence of dither</title>

Security, Steganography, and Watermarking of Multimedia Contents VII, 2005

Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves th... more Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. The existence of good high dimensional lattices that can be efficiently implemented and incorporated into watermarking structures, made quantization-based watermarking schemes of practical interest. Because of the structure of the lattices, watermarking schemes making use of them are vulnerable to non-additive operations, like amplitude scaling in combination with additive noise. In this paper, we propose a secure Maximum Likelihood (ML) estimation technique for amplitude scaling factors using subtractive dither. The dither has mainly security purposes and is assumed to be known to the watermark encoder and decoder. We derive the probability density function (PDF) models of the watermarked and attacked data in the presence of subtractive dither. The derivation of these models follows the lines of reference 5, where we derived the PDF models in the absence of dither. We derive conditions for the dither sequence statistics such that a given security level is achieved using the error probability of the watermarking system as objective function. Based on these conditions we are able to make approximations to the PDF models that are used in the ML estimation procedure. Finally, experiments are performed with real audio and speech signals showing the good performance of the proposed estimation technique under realistic conditions.

Research paper thumbnail of <title>Scale estimation in two-band filter attacks on QIM watermarks</title>

Security, Steganography, and Watermarking of Multimedia Contents VIII, 2006

This paper presents a scheme for estimating two-band amplitude scale attack within a quantization... more This paper presents a scheme for estimating two-band amplitude scale attack within a quantization-based watermarking context. Quantization-based watermarking schemes comprise a class of watermarking schemes that achieves the channel capacity in terms of additive noise attacks. Unfortunately, Quantization-based watermarking schemes are not robust against Linear Time Invariant (LTI) filtering attacks. We concentrate on a multi-band amplitude scaling attack that modifies

Research paper thumbnail of <title>Statistical amplitude scale estimation for quantization-based watermarking</title>

Security, Steganography, and Watermarking of Multimedia Contents VI, 2004

Research paper thumbnail of Estimation of attacker's scale and noise variance for qim-dc watermark embedding

2004 International Conference on Image Processing, 2004. ICIP '04., 2004

... 56 paper, wc refrain from explicitly modeling this effect, but take the dithering of the quan... more ... 56 paper, wc refrain from explicitly modeling this effect, but take the dithering of the quantizers into account ... tings have been used to benchmark the estimation proce-dure ... following table list our current results based on synthetic (Gaussian) data, with = 0.91, watermark-to-signal ...

Research paper thumbnail of Amplitude Scale Estimation for Quantization-Based Watermarking

IEEE Transactions on Signal Processing, 2000

In this paper we propose a maximum likelihood technique to combat amplitude scaling attacks withi... more In this paper we propose a maximum likelihood technique to combat amplitude scaling attacks within a quantizationbased watermarking context. We concentrate on operations that are common in many applications and at the same time devastating to this class of watermarking schemes, namely, amplitude scaling in combination with additive noise. First we derive the probability density function of the watermarked and attacked data in the absence of subtractive dither. Next we extend these models to incorporate subtractive dither in the encoder. The dither sequence is primarily used for security purposes, and the dither is assumed to be known also to the decoder. We design the dither signal statistics such that an attacker having no knowledge of the dither cannot decode the watermark. Using an approximation of the probability density function in the presence of subtractive dither, we derive a maximum likelihood procedure for estimating amplitude scaling factors. Experiments are performed with synthetic and real audio signals, showing the feasibility of the proposed approach under realistic conditions. Index Terms-Maximum likelihood estimation, probability of error, quantization, statistics, subtractive dither, watermarking.

Research paper thumbnail of permGPU : Using graphics processing units in RNA microarray association studies

Bmc Bioinformatics, 2010

Background: Many analyses of microarray association studies involve permutation, bootstrap resamp... more Background: Many analyses of microarray association studies involve permutation, bootstrap resampling and crossvalidation, that are ideally formulated as embarrassingly parallel computing problems. Given that these analyses are computationally intensive, scalable approaches that can take advantage of multi-core processor systems need to be developed.

Research paper thumbnail of Pharmacogenetic Discovery in CALGB (Alliance) 90401 and Mechanistic Validation of a VAC14 Polymorphism That Increases Risk of Docetaxel-Induced Neuropathy

Clinical cancer research : an official journal of the American Association for Cancer Research, Jan 3, 2016

Discovery of single nucleotide polymorphisms (SNPs) that predict a patient's risk of docetaxe... more Discovery of single nucleotide polymorphisms (SNPs) that predict a patient's risk of docetaxel-induced neuropathy would enable treatment individualization to maximize efficacy and avoid unnecessary toxicity. The objectives of this analysis were to discover SNPs associated with docetaxel-induced neuropathy and mechanistically validate these associations in preclinical models of drug-induced neuropathy. A genome-wide association study was conducted in metastatic castrate-resistant prostate cancer patients treated with docetaxel, prednisone and randomized to bevacizumab or placebo on CALGB 90401. SNPs were genotyped on the Illumina HumanHap610-Quad platform followed by rigorous quality control. The inference was conducted on the cumulative dose at occurrence of grade 3+ sensory neuropathy using a cause-specific hazard model that accounted for early treatment discontinuation. Genes with SNPs significantly associated with neuropathy were knocked down in cellular and mouse models of d...

Research paper thumbnail of Tumor markers of efficacy and resistance to cetuximab (C) treatment in metastatic colorectal cancer (mCRC): Results from CALGB 80203 (Alliance)

Asco Meeting Abstracts, May 20, 2013

Research paper thumbnail of A genome-wide association study (GWAS) of docetaxel-induced peripheral neuropathy in CALGB 90401 (Alliance)

Asco Meeting Abstracts, May 20, 2013

Research paper thumbnail of Gene Expression Markers of Efficacy and Resistance to Cetuximab Treatment in Metastatic Colorectal Cancer: Results from CALGB 80203 (Alliance)

Clinical Cancer Research, 2014

Purpose: Formalin-fixed, paraffin-embedded tumor samples from CALGB 80203 were analyzed for expre... more Purpose: Formalin-fixed, paraffin-embedded tumor samples from CALGB 80203 were analyzed for expression of EGFR axisrelated genes to identify prognostic or predictive biomarkers for cetuximab treatment.

Research paper thumbnail of Hierarchical kernel stick-breaking process for multi-task image analysis

Proceedings of the 25th international conference on Machine learning - ICML '08, 2008

The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the con... more The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the condition that patches (small blocks of pixels) that are spatially proximate are more likely to be associated with the same cluster (segment). The number of clusters is not set a priori and is inferred from the hierarchical Bayesian model. Further, KSBP is integrated with a shared Dirichlet process prior to simultaneously model multiple images, inferring their inter-relationships. This latter application may be useful for sorting and learning relationships between multiple images. The Bayesian inference algorithm is based on a hybrid of variational Bayesian analysis and local sampling. In addition to providing details on the model and associated inference framework, example results are presented for several image-analysis problems.

Research paper thumbnail of Integration of Cell Line and Clinical Trial Genome-Wide Analyses Supports a Polygenic Architecture of Paclitaxel-Induced Sensory Peripheral Neuropathy

Clinical Cancer Research, 2013

Purpose: We sought to show the relevance of a lymphoblastoid cell line (LCL) model in the discove... more Purpose: We sought to show the relevance of a lymphoblastoid cell line (LCL) model in the discovery of clinically relevant genetic variants affecting chemotherapeutic response by comparing LCL genome-wide association study (GWAS) results to clinical GWAS results.

Research paper thumbnail of permGPU: Using graphics processing units in RNA microarray association studies

BMC Bioinformatics, 2010

Background: Many analyses of microarray association studies involve permutation, bootstrap resamp... more Background: Many analyses of microarray association studies involve permutation, bootstrap resampling and crossvalidation, that are ideally formulated as embarrassingly parallel computing problems. Given that these analyses are computationally intensive, scalable approaches that can take advantage of multi-core processor systems need to be developed.

Research paper thumbnail of Security, Steganography, and Watermarking of Multimedia Contents VIII (Proceedings Volume)

The contribution of this paper is two-fold. First, we describe an improved version of a blind ste... more The contribution of this paper is two-fold. First, we describe an improved version of a blind steganalysis method previously proposed by Holotyak et al. and compare it to current state-of-the-art blind steganalyzers. The features for the blind classifier are calculated in the wavelet domain as higher-order absolute moments of the noise residual. This method clearly shows the benefit of calculating the features from the noise residual because it increases the features' sensitivity to embedding, which leads to improved detection results ...

Research paper thumbnail of Bayesian Watermark Attacks

This paper presents an application of statistical machine learning to the field of watermarking. ... more This paper presents an application of statistical machine learning to the field of watermarking. We propose a new attack model on additive spread-spectrum watermarking systems. The proposed attack is based on Bayesian statistics. We consider the scenario in which a watermark signal is repeatedly embedded in specific, possibly chosen based on a secret message bitstream, segments (signals) of the host data. The host signal can represent a patch of pixels from an image or a video frame. We propose a probabilistic model that infers the embedded message bitstream and watermark signal, directly from the watermarked data, without access to the decoder. We develop an efficient Markov chain Monte Carlo sampler for updating the model parameters from their conjugate full conditional posteriors. We also provide a variational Bayesian solution, which further increases the convergence speed of the algorithm. Experiments with synthetic and real image signals demonstrate that the attack model is able to correctly infer a large part of the message bitstream and obtain a very accurate estimate of the watermark signal.