Biblio

Training deep neural networks is a computationally expensive task. Furthermore, models are often derived from proprietary datasets that have been carefully prepared and labelled. Hence, creators of deep learning models want to protect their models against intellectual property theft. However, this is not always possible, since the model may, e.g., be embedded in a mobile app for fast response times. As a countermeasure watermarks for deep neural networks have been developed that embed secret information into the model. This information can later be retrieved by the creator to prove ownership. Uchida et al. proposed the first such watermarking method. The advantage of their scheme is that it does not compromise the accuracy of the model prediction. However, in this paper we show that their technique modifies the statistical distribution of the model. Using this modification we can not only detect the presence of a watermark, but even derive its embedding length and use this information to remove the watermark by overwriting it. We show analytically that our detection algorithm follows consequentially from their embedding algorithm and propose a possible countermeasure. Our findings shall help to refine the definition of undetectability of watermarks for deep neural networks.

Recently in the vast advancement of Artificial Intelligence, Machine learning and Deep Neural Network (DNN) driven us to the robust applications. Such as Image processing, speech recognition, and natural language processing, DNN Algorithms has succeeded in many drawbacks; especially the trained DNN models have made easy to the researchers to produces state-of-art results. However, sharing these trained models are always a challenging task, i.e. security, and protection. We performed extensive experiments to present some analysis of watermark in DNN. We proposed a DNN model for Digital watermarking which investigate the intellectual property of Deep Neural Network, Embedding watermarks, and owner verification. This model can generate the watermarks to deal with possible attacks (fine tuning and train to embed). This approach is tested on the standard dataset. Hence this model is robust to above counter-watermark attacks. Our model accurately and instantly verifies the ownership of all the remotely expanded deep learning models without affecting the model accuracy for standard information data.

This paper presents a scheme of intellectual property protection of hardware circuit based on digital compression coding technology. The aim is to solve the problem of high embedding cost and low resource utilization of IP watermarking. In this scheme, the watermark information is preprocessed by dynamic compression coding around the idle circuit of FPGA, and the free resources of the surrounding circuit are optimized that the IP watermark can get the best compression coding model while the extraction and detection of IP core watermark by activating the decoding function. The experimental results show that this method not only expands the capacity of watermark information, but also reduces the cost of watermark and improves the security and robustness of watermark algorithm.

This paper proposes an audio watermarking algorithm having good balance between perceptual transparency, robustness, and payload. The proposed algorithm is based on Cordic QR decomposition and multi-resolution decomposition meeting all the necessary audio watermarking design requirements. The use of Cordic QR decomposition provides good robustness and use of detailed coefficients of multi-resolution decomposition help to obtain good transparency at high payload. Also, the proposed algorithm does not require original signal or the embedded watermark for extraction. The binary data embedding capacity of the proposed algorithm is 960.4 bps and the highest SNR obtained is 35.1380 dB. The results obtained in this paper show that the proposed method has good perceptual transparency, high payload and robustness under various audio signal processing attacks.

Digital images are extensively used and exchanged through internet, which gave rise to the need of establishing authorship of images. Image watermarking has provided a solution to prevent false claims of ownership of the media. Information about the owner, generally in the form of a logo, text or image is imperceptibly hid into the subject. Many transforms have been explored by the researcher community for image watermarking. Many watermarking techniques have been developed based on Singular Value Decomposition (SVD) of images. This paper analyses Singular Value Decomposition to understand its use, ability and limitations to hide additional information into the cover image for Digital Image Watermarking application.

A key challenge of the embedded era is to ensure trust in reuse of intellectual properties (IPs), which facilitates reduction of design cost and meeting of stringent marketing deadlines. Determining source of the IPs or their authenticity is a key metric to facilitate safe reuse of IPs. Though physical unclonable functions solves this problem for application specific integrated circuit (ASIC) IPs, authentication strategies for reconfigurable IPs (RIPs) or IPs of reconfigurable hardware platforms like field programmable gate arrays (FPGAs) are still in their infancy. Existing authentication techniques for RIPs that relies on verification of proof of authentication (PoA) mark embedded in the RIP by the RIP producers, leak useful clues about the PoA mark. This results in replication and implantation of the PoA mark in fake RIPs. This not only causes loss to authorized second hand RIP users, but also poses risk to the reputation of the RIP producers. We propose a zero knowledge authentication strategy for safe reusing of RIPs. The PoA of an RIP producer is kept secret and verification is carried out based on traversal times from the initial point to several intermediate points of the embedded PoA when the RIPs configure an FPGA. Such delays are user specific and cannot be replicated as these depend on intrinsic properties of the base semiconductor material of the FPGA, which is unique and never same as that of another FPGA. Experimental results validate our proposed mechanism. High strength even for low overhead ISCAS benchmarks, considered as PoA for experimentation depict the prospects of our proposed methodology.

The integrity and reliability of speech data have been important issues to probative use. Watermarking technologies supplies an alternative solution to guarantee the the authenticity of multiple data besides digital signature. This work proposes a novel digital watermarking based on a reversible compression algorithm with sample scanning to detect tampering in time domain. In order to detect tampering precisely, the digital speech data is divided into length-fixed frames and the content-based hash information of each frame is calculated and embedded into the speech data for verification. Huffman compression algorithm is applied to each four sampling bits from least significant bit in each sample after pulse-code modulation processing to achieve low distortion and high capacity for hiding payload. Experimental experiments on audio quality, detection precision and robustness towards attacks are taken, and the results show the effectiveness of tampering detection with a precision with an error around 0.032 s for a 10 s speech clip. Distortion is imperceptible with an average 22.068 dB for Huffman-based and 24.139 dB for intDCT-based method in terms of signal-to-noise, and with an average MOS 3.478 for Huffman-based and 4.378 for intDCT-based method. The bit error rate (BER) between stego data and attacked stego data in both of time-domain and frequency domain is approximate 28.6% in average, which indicates the robustness of the proposed hiding method.

The return-oriented programming(ROP) attack has been a common access to exploit software vulnerabilities in the modern operating system(OS). An attacker can execute arbitrary code with the aid of ROP despite security mechanisms are involved in OS. In order to mitigate ROP attack, defense mechanisms are also drawn researchers' attention. Besides, research on the benign use of ROP become a hot spot in recent years, since ROP has a perfect resistance to static analysis, which can be adapted to hide some important code. The results in benign use also benefit from a low overhead on program size. The paper discusses the concepts of ROP attack as well as extended ROP attack in recent years. Corresponding defense mechanisms based on randomization, frequency, and control flow integrity are analyzed as well, besides, we also analyzed limitations in this defense mechanisms. Later, we discussed the benign use of ROP in steganography, code integrity verification, and software watermarking, which showed the significant promotion by adopting ROP. At the end of this paper, we looked into the development of ROP attack, the future of possible mitigation strategies and the potential for benign use.

Publically available relational data without security protection may cause data protection issues. Watermarking facilitates solution for remote sharing of relational database by ensuring data integrity and security. In this research, a reversible watermarking for numerical relational database by using evolutionary technique has been proposed that ensure the integrity of underlying data and robustness of watermark. Moreover, mRMR based feature subset selection technique has been used to select attributes for implementation of watermark instead of watermarking whole database. Binary Bat algorithm has been used as constraints optimization technique for watermark creation. Experimental results have shown the effectiveness of the proposed technique against data tempering attacks. In case of alteration attacks, almost 70% data has been recovered, 50% in deletion attacks and 100% data is retrieved after insertion attacks. The watermarking based on evolutionary technique (WET) i.e., mRMR based Binary Bat Algorithm ensures the data accuracy and it is resilient against malicious attacks.

The barcode is an important link between real life and the virtual world nowadays. One of the most common barcodes is QR code, which its appearance, black and white modules, is not visually pleasing. The QR code is applied to product packaging and campaign promotion in the market. There are more and more stores using QR code for transaction payment. If the QR code is altered or illegally duplicated, it will endanger the information security of users. Therefore, the study uses infrared watermarking to embed the infrared QR code information into the explicit QR code to strengthen the anti-counterfeiting features. The explicit graphic QR code is produced by data hiding with error diffusion in this study. With the optical characteristics of K, one of the four printed ink colors CMYK (Cyan, Magenta, Yellow, Black), only K can be rendered in infrared. Hence, we use the infrared watermarking to embed the implicit QR code information into the explicit graphic QR code. General QR code reader may be used to interpret explicit graphic QR code information. As for implicit QR code, it needs the infrared detector to extract its implicit QR code information. If the QR code is illegally copied, it will not show the hidden second QR code under infrared detection. In this study, infrared watermark hidden in the graphic QR code can enhance not only the aesthetics of QR code, but also the anti-counterfeiting feature. It can also be applied to printing related fields, such as security documents, banknotes, etc. in the future.

A multipurpose color image watermarking method is presented to provide \textcopyright protection and ownership verification of the multimedia information. For robust color image watermarking, color watermark is utilized to bring universality and immense applicability to the proposed scheme. The cover information is first converted to Red, Green and Blue components image. Each component is transformed in wavelet domain using DWT (Discrete Wavelet Transform) and then decomposition techniques like Singular Value Decomposition (SVD), QR and Schur decomposition are applied. Multiple watermark embedding provides the watermarking scheme free from error (false positive). The watermark is modified by scrambling it using Arnold transform. In the proposed watermarking scheme, robustness and quality is tested with metrics like Peak Signal to Noise Ratio (PSNR) and Normalized Correlation Coefficient (NCC). Further, the proposed scheme is compared with related watermarking schemes.

This paper presents an image technique Discrete Wavelet Transform and Singular Value Decomposition for image steganography. We are using a text file and convert into an image as watermark and embed watermarks into the cover image. We evaluate performance and compare this method with other methods like Least Significant Bit, Discrete Cosine Transform, and Discrete Wavelet Transform using Peak Signal Noise Ratio and Mean Squared Error. The result of this experiment showed that combine of Discrete Wavelet Transform and Singular Value Decomposition performance is better than the Least Significant Bit, Discrete Cosine Transform, and Discrete Wavelet Transform. The result of Peak Signal Noise Ratio obtained from Discrete Wavelet Transform and Singular Value Decomposition method is 57.0519 and 56.9520 while the result of Mean Squared Error is 0.1282 and 0.1311. Future work for this research is to add the encryption method on the data to be entered so that if there is an attack then the encryption method can secure the data becomes more secure.

Image hiding is the important tools to protect the ownership rights of digital multimedia contents. To reduce the interference effect of the host signal in the popular Spread Spectrum (SS) image hiding algorithm, this paper proposes an Improved Additive Spread Spectrum (IASS) image hiding algorithm. The proposed IASS image hiding algorithm maintains the simple decoder of the Additive Spread Spectrum (ASS) image hiding algorithm. This paper makes the comparative experiments with the ASS image hiding algorithm and Correlation-and-bit-Aware Spread Spectrum (CASS) image hiding algorithm. For the noise-free scenario, the proposed IASS image hiding algorithm could yield error-free decoding performance in theory. For the noise scenario, the experimental results show that the proposed IASS image hiding algorithm could significantly reduce the host effect in data hiding and improve the watermark decoding performance remarkably.

With the rapid development of computer networks, multimedia information is widely used, and the security of digital media has drawn much attention. The revised photo as a forensic evidence will distort the truth of the case badly tampered pictures on the social network can have a negative impact on the parties as well. In order to ensure the authenticity and integrity of digital media, self-recovery of digital images based on information hiding is studied in this paper. Jarvis half-tone change is used to compress the digital image and obtain the backup data, and then spread the backup data to generate the reference data. Hash algorithm aims at generating hash data by calling reference data and original data. Reference data and hash data together as a digital watermark scattered embedded in the digital image of the low-effective bits. When the image is maliciously tampered with, the hash bit is used to detect and locate the tampered area, and the image self-recovery is performed by extracting the reference data hidden in the whole image. In this paper, a thorough rebuild quality assessment of self-healing images is performed and better performance than the traditional DCT(Discrete Cosine Transform)quantization truncation approach is achieved. Regardless of the quality of the tampered content, a reference authentication system designed according to the principles presented in this paper allows higher-quality reconstruction to recover the original image with good quality even when the large area of the image is tampered.

Organizations not only need to defend their IT systems against external cyber attackers, but also from malicious insiders, that is, agents who have infiltrated an organization or malicious members stealing information for their own profit. In particular, malicious insiders can leak a document by simply opening it and taking pictures of the document displayed on the computer screen with a digital camera. Using a digital camera allows a perpetrator to easily avoid a log trail that results from using traditional communication channels, such as sending the document via email. This makes it difficult to identify and prove the identity of the perpetrator. Even a policy prohibiting the use of any device containing a camera cannot eliminate this threat since tiny cameras can be hidden almost everywhere. To address this leakage vector, we propose a novel screen watermarking technique that embeds hidden information on computer screens displaying text documents. The watermark is imperceptible during regular use, but can be extracted from pictures of documents shown on the screen, which allows an organization to reconstruct the place and time of the data leak from recovered leaked pictures. Our approach takes advantage of the fact that the human eye is less sensitive to small luminance changes than digital cameras. We devise a symbol shape that is invisible to the human eye, but still robust to the image artifacts introduced when taking pictures. We complement this symbol shape with an error correction coding scheme that can handle very high bit error rates and retrieve watermarks from cropped and compressed pictures. We show in an experimental user study that our screen watermarks are not perceivable by humans and analyze the robustness of our watermarks against image modifications.

Least Significant Bit (LSB) as one of steganography methods that already exist today is really mainstream because easy to use, but has weakness that is too easy to decode the hidden message. It is because in LSB the message embedded evenly to all pixels of an image. This paper introduce a method of steganography that combine LSB with clustering method that is Fuzzy C-Means (FCM). It is abbreviated with LSB\_FCM, then compare the stegano result with LSB method. Each image will divided into two cluster, then the biggest cluster capacity will be choosen, finally save the cluster coordinate key as place for embedded message. The key as a reference when decode the message. Each image has their own cluster capacity key. LSB\_FCM has disadvantage that is limited place to embedded message, but it also has advantages compare with LSB that is LSB\_FCM have more difficulty level when decrypted the message than LSB method, because in LSB\_FCM the messages embedded randomly in the best cluster pixel of an image, so to decrypted people must have the cluster coordinate key of the image. Evaluation result show that the MSE and PSNR value of LSB\_FCM some similiar with the pure LSB, it means that LSB\_FCM can give imperceptible image as good as the pure LSB, but have better security from the embedding place.

Deep learning technologies, which are the key components of state-of-the-art Artificial Intelligence (AI) services, have shown great success in providing human-level capabilities for a variety of tasks, such as visual analysis, speech recognition, and natural language processing and etc. Building a production-level deep learning model is a non-trivial task, which requires a large amount of training data, powerful computing resources, and human expertises. Therefore, illegitimate reproducing, distribution, and the derivation of proprietary deep learning models can lead to copyright infringement and economic harm to model creators. Therefore, it is essential to devise a technique to protect the intellectual property of deep learning models and enable external verification of the model ownership. In this paper, we generalize the "digital watermarking'' concept from multimedia ownership verification to deep neural network (DNNs) models. We investigate three DNN-applicable watermark generation algorithms, propose a watermark implanting approach to infuse watermark into deep learning models, and design a remote verification mechanism to determine the model ownership. By extending the intrinsic generalization and memorization capabilities of deep neural networks, we enable the models to learn specially crafted watermarks at training and activate with pre-specified predictions when observing the watermark patterns at inference. We evaluate our approach with two image recognition benchmark datasets. Our framework accurately (100$\backslash$%) and quickly verifies the ownership of all the remotely deployed deep learning models without affecting the model accuracy for normal input data. In addition, the embedded watermarks in DNN models are robust and resilient to different counter-watermark mechanisms, such as fine-tuning, parameter pruning, and model inversion attacks.

The evolution of cloud gaming systems is substantially the security requirements for computer games. Although online game development often utilizes artificial intelligence and human computer interaction, game developers and providers often do not pay much attention to security techniques. In cloud gaming, location-based games are augmented reality games which take the original principals of the game and applies them to the real world. In other terms, it uses the real world to impact the game experience. Because the execution of such games is distributed in cloud computing, users cannot be certain where their input and output data are managed. This introduces the possibility to input incorrect data in the exchange between the gamer's terminal and the gaming platform. In this context, we propose a new gaming concept for augmented reality and location-based games in order to solve the aforementioned cheating scenario problem. The merit of our approach is to establish an accurate and verifiable proof that the gamer reached the goal or found the target. The major novelty in our method is that it allows the gamer to submit an authenticated proof related to the game result without altering the privacy of positioning data.

The Internet of Things (IoT) is the latest Internet evolution that interconnects billions of devices, such as cameras, sensors, RFIDs, smart phones, wearable devices, ODBII dongles, etc. Federations of such IoT devices (or things) provides the information needed to solve many important problems that have been too difficult to harness before. Despite these great benefits, privacy in IoT remains a great concern, in particular when the number of things increases. This presses the need for the development of highly scalable and computationally efficient mechanisms to prevent unauthorised access and disclosure of sensitive information generated by things. In this paper, we address this need by proposing a lightweight, yet highly scalable, data obfuscation technique. For this purpose, a digital watermarking technique is used to control perturbation of sensitive data that enables legitimate users to de-obfuscate perturbed data. To enhance the scalability of our solution, we also introduce a contextualisation service that achieve real-time aggregation and filtering of IoT data for large number of designated users. We, then, assess the effectiveness of the proposed technique by considering a health-care scenario that involves data streamed from various wearable and stationary sensors capturing health data, such as heart-rate and blood pressure. An analysis of the experimental results that illustrate the unconstrained scalability of our technique concludes the paper.

For the increasing use of internet, it is equally important to protect the intellectual property. And for the protection of copyright, a blind digital watermark algorithm with SVD and OSELM in the IWT domain has been proposed. During the embedding process, SVD has been applied to the coefficient blocks to get the singular values in the IWT domain. Singular values are modulated to embed the watermark in the host image. Online sequential extreme learning machine is trained to learn the relationship between the original coefficient and the corresponding watermarked version. During the extraction process, this trained OSELM is used to extract the embedded watermark logo blindly as no original host image is required during this process. The watermarked image is altered using various attacks like blurring, noise, sharpening, rotation and cropping. The experimental results show that the proposed watermarking scheme is robust against various attacks. The extracted watermark has very much similarity with the original watermark and works good to prove the ownership.

The utilization of the online services especially the access to Internet Banking services has grown rapidly from last five years. The Internet Banking services provide the customers with the secure and reliable environment to deal with. But with the technology advancement, it is mandatory for the banks to put into practice the ideal technologies or the best security strategies and procedures to authorize or validate the originality of the customers. This must be done to ensure that the data or the information being transmitted during any kind of transaction is safe and no kind of leakage or modification of the information is possible for the intruder. This paper presents a digital watermark method for the QR Code (Quick Response Code) In this, a visible watermark is embedded in the QR Code image using the watermark technology (DCT) and describes the functioning feature of a secure authorization system by means of QR codes & the digital watermark for Internet Banking.

Being an era of fast internet-based application environment, large volumes of relational data are being outsourced for business purposes. Therefore, ownership and digital rights protection has become one of the greatest challenges and among the most critical issues. This paper presents a novel fingerprinting technique to protect ownership rights of non-numeric digital data on basis of pattern generation and row association schemes. Firstly, fingerprint sequence is formulated by using secret key and buyer's Unique ID. With the chunks of these sequences and by applying the Fibonacci series, we select some rows. The selected rows are candidates of fingerprinting. The primary key of selected row is protected using RSA encryption; after which a pattern is designed by randomly choosing the values of different attributes of datasets. The encryption of primary key leads to develop an association between original and fake pattern; creating an ease in fingerprint detection. Fingerprint detection algorithm first finds the fake rows and then extracts the fingerprint sequence from the fake attributes, hence identifying the traitor. Some most important features of the proposed approach is to overcome major weaknesses such as error tolerance, integrity and accuracy in previously proposed fingerprinting techniques. The results show that technique is efficient and robust against several malicious attacks.

Our position is that a key component of securing cyber-physical systems (CPS) is to develop a theory of accountability that encompasses both control and computing systems. We envision that a unified theory of accountability in CPS can be built on a foundation of causal information flow analysis. This theory will support design and analysis of mechanisms at various stages of the accountability regime: attack detection, responsibility-assignment (e.g., attack identification or localization), and corrective measures (e.g., via resilient control) As an initial step in this direction, we summarize our results on attack detection in control systems. We use the Kullback-Liebler (KL) divergence as a causal information flow measure. We then recover, using information flow analyses, a set of existing results in the literature that were previously proved using different techniques. These results cover passive detection, stealthy attack characterization, and active detection. This research direction is related to recent work on accountability in computational systems [1], [2], [3], [4]. We envision that by casting accountability theories in computing and control systems in terms of causal information flow, we can provide a common foundation to develop a theory for CPS that compose elements from both domains.

The Internet of Things (IoT) has become ubiquitous in our daily life as billions of devices are connected through the Internet infrastructure. However, the rapid increase of IoT devices brings many non-traditional challenges for system design and implementation. In this paper, we focus on the hardware security vulnerabilities and ultra-low power design requirement of IoT devices. We briefly survey the existing design methods to address these issues. Then we propose an approximate computing based information hiding approach that provides security with low power. We demonstrate that this security primitive can be applied for security applications such as digital watermarking, fingerprinting, device authentication, and lightweight encryption.

Multimedia security and copyright protection has been a popular topic for research and application, due to the explosion of data exchange over the internet and the widespread use of digital media. Watermarking is a process of hiding the digital information inside a digital media. Information hiding as digital watermarks in multimedia enables protection mechanism in decrypted contents. This paper presents a comparative study of existing technique used for digital watermarking an image using Genetic Algorithm and Bacterial Foraging Algorithm (BFO) based optimization technique with proposed one which consists of Genetic Algorithm and Honey Bee based optimization technique. The results obtained after experiment conclude that, new method has indeed outperformed then the conventional technique. The implementation is done over the MATLAB.