VLDB 2026 Research / reviewers in the wild / expert
Amirhossein Taherinia
dblp:03/5465 · also Amir Hossein Taherinia
· DBLP profile ↗
18ranked-venue papers
3as first author
6since 2021 · last 2023
0000-0002-5103-4812ORCID · verified
Domains — the database's venue-derived domains; a paper can count in several
Graphics, computer vision, multimedia, augmented reality and games · 9 · 3 since 2021Security and privacy · 5 · 3 first-author · 2 since 2021Artificial intelligence and machine learning · 2Databases, data management, data science and information retrieval · 2 · 1 since 2021
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2023 | Management of the optimizer's curse concept in single-task diffusion networks
Atieh Gharib, Hadi Sadoghi Yazdi, Amirhossein Taherinia |
Inf. Sci. | 3 |
| 2023 | Image steganography based on smooth cycle-consistent adversarial learning
Behnaz Abdollahi, Ahad Harati, Amirhossein Taherinia |
J. Inf. Secur. Appl. | 3 |
| 2023 | Fast and accurate image retrieval using knowledge distillation from multiple deep pre-trained networks
Hasan Salman, Amirhossein Taherinia, Davoud Zabihzadeh |
Multim. Tools Appl. | 2 |
| 2022 | Non-additive image steganographic framework based on variational inference in Markov Random Fields
Behnaz Abdollahi, Ahad Harati, Amirhossein Taherinia |
J. Inf. Secur. Appl. | 3 |
| 2022 | A passive image forensic scheme based on an adaptive and hybrid techniques
Manaf Mohammed Ali Alhaidery, Amirhossein Taherinia |
Multim. Tools Appl. | 2 |
| 2022 | Cloning detection scheme based on linear and curvature scale space with new false positive removal filters
Manaf Mohammed Ali Alhaidery, Amirhossein Taherinia, Hadi Sadoghi Yazdi |
Multim. Tools Appl. | 2 |
| 2020 | Analysis of robust recursive least squares: Convergence and tracking
Alireza Naeimi Sadigh, Amirhossein Taherinia, Hadi Sadoghi Yazdi |
Signal Process. | 2 |
| 2019 | Crowd analysis using Bayesian Risk Kernel Density Estimation
Mahnaz Razavi, Hadi Sadoghi Yazdi, Amirhossein Taherinia |
Eng. Appl. Artif. Intell. | 3 |
| 2019 | TRLG: Fragile blind quad watermarking for image tamper detection and recovery by providing compact digests with optimized quality using LWT and GA
Behrouz Bolourian Haghighi, Amirhossein Taherinia, Amir Hossein Mohajerzadeh |
Inf. Sci. | 2 |
| 2019 | A probabilistic framework for copy-move forgery detection based on Markov Random Field
Behnaz Elhaminia, Ahad Harati, Amirhossein Taherinia |
Multim. Tools Appl. | 3 |
| 2019 | WACA: a new blind robust watermarking method based on Arnold Cat map and amplified pseudo-noise strings with weak correlation
Seyyed Hossein Soleymani, Amirhossein Taherinia, Amir Hossein Mohajerzadeh |
Multim. Tools Appl. | 2 |
| 2018 | Robust Semi-Supervised Growing Self-Organizing Map
Ali Mehrizi, Hadi Sadoghi Yazdi, Amirhossein Taherinia |
Expert Syst. Appl. | 3 |
| 2018 | TRLH: Fragile and blind dual watermarking for image tamper detection and self-recovery based on lifting wavelet transform and halftoning technique
Behrouz Bolourian Haghighi, Amirhossein Taherinia, Ahad Harati |
J. Vis. Commun. Image Represent. | 2 |
| 2017 | Double expanding robust image watermarking based on Spread Spectrum technique and BCH coding
Seyyed Hossein Soleymani, Amirhossein Taherinia |
Multim. Tools Appl. | 2 |
| 2017 | High capacity image steganography on sparse message of scanned document image (SMSDI)
Seyyed Hossein Soleymani, Amirhossein Taherinia |
Multim. Tools Appl. | 2 |
| 2012 | A two-step watermarking attack using long-range correlation image restorationabstractABSTRACT This paper presents an efficient scheme for blind watermark attacking using the concept of matching of the long‐range data. The main idea of the proposed attack is to add plenty of noise to the watermarked image and then try to restore an unwatermarked copy of the noisy image. The aim is to destroy the watermark information without accessing the parameters used during the watermark embedding process. So, it allows our approach to be completely free from any pre‐assumption on the watermarking algorithm or any other parameters that is used during the watermark embedding procedure. Experimental results show the proposed algorithm's superiority over several other traditional watermarking benchmarks such as Stirmark and Optimark. Peak signal‐to‐noise ratio of the watermarked image after applying the proposed attack is more than 45 dB, and the normalized cross‐correlation for the extracted watermark is lower than 0·4, so the watermark is not detectable after our attack. Copyright © 2011 John Wiley & Sons, Ltd. Amirhossein Taherinia, Mansour Jamzad |
Secur. Commun. Networks | 1 |
| 2009 | A New Watermarking Attack Using Long-Range Correlation Image RestorationabstractIn this paper, we propose a new method for damaging and destroying robust invisible watermarks using an image restoration technique which is called long-range correlation. The restoration technique is based on the concept of the general long-range correlation within natural images. First we add some random noise to the watermarked image, and then by using the restoration technique we restore the destroyed pixels. Restored image has high correlation with the watermarked image but due to some modifications that the restoration process made in the watermarked image, the hidden watermark is destroyed. We have tested the proposed method to attack two recent and robust watermarking methods and the results sound impressive. PSNR of the watermarked image after applying the proposed attack is more than 45 dB and the NC for the extracted watermark is lower than 0.4, so it is not detectable. Moreover, the proposed method does not consider any knowledge about the underlying watermarking algorithm. Amirhossein Taherinia, Mehran Fotouhi, Mansour Jamzad |
ARES | 1 |
| 2009 | A Robust Image Watermarking Using Two Level DCT and Wavelet Packets DenoisingabstractIn this paper we present a blind low frequency watermarking scheme on gray level images, which is based on DCT transform and spread spectrum communications technique. We compute the DCT of non overlapping 8times8 blocks of the hostimage, then using the DC coefficients of each block we construct a low-resolution approximation image. We apply block based DCT on this approximation image, then a pseudo random noise sequence is added into its high frequencies. For detection, we extract the approximation image from the watermarked image, then the same pseudo random noise sequence is generated, and its correlation is computed with high frequencies of the watermarked approximation image. In our method, higher robustness is obtained because of embedding the watermark in low frequency. In addition, higher imperceptibility is gained by scattering the watermark's bit in different blocks. We evaluated the robustness of the proposed technique against many common attacks such as JPEG compression, additive Gaussian noise and median filter. Compared with related works, our method proved to be highly resistant in cases of compression and additive noise, while preserving high PSNR for the watermarked images. Amirhossein Taherinia, Mansour Jamzad |
ARES | 1 |