International Journal of Advance Engineering and Research Development. Privacy Decision for controlling Photo Sharing on Online Social Network

Transcription

1 Scientific Journal of Impact Factor (SJIF): 4.72 International Journal of Advance Engineering and Research Development Volume 4, Issue 5, May-2017 Privacy Decision for controlling Photo Sharing on Online Social Network Kapil Pardeshi 1, Dhiraj Patil 2, Raju Naikare 3, Ninad Chhatre 4 Prof. Deepak Gupta 5 1,2,3,4,5 Computer Engineering, Siddhant College of Engineering, Pune e-issn (O): p-issn (P): Abstract Photo sharing is a charming component which progresses Online Social Networks (OSNs). Unfortunately, it might release users security if they are allowed to post, comment, and mark a photo openly. In this paper, we try to address this issue and study the situations when a user shares a photo containing individuals other than him/her. To anticipate possible security spillage of a photo, we designed a system to enable each individual in a photo aware of the posting activity and share in the decision making on the photo posting. Consequently, we require a capable facial acknowledgement (FR) structure that can see everyone in the photo. In any case, all the additionally asking for security setting may control the photos quantity freely available to design the FR system. To deal with this issue, our system attempts to utilize users private photos to arrange an altered FR system especially arranged to isolate possible photo co-proprietors without releasing their privacy. We also add to a disseminated accords based framework to reduce the computational versatile quality and guarantee the private get ready set. We exhibit that our system is superior to anything other possible procedures to the extent acknowledgment extent and adequacy i.e. effectiveness. Keywords- Social network, photo privacy, secure multi-party computation, support, vector machine, collaborative learning I. INTRODUCTION The massive use of social networking sites and with the vogue of photo sharing on social networking sites users naively tends to share personal information. Social networking users may or may not be aware of getting their personal information to be leaked or will benefit the malevolent hackers or may commit any kind of privacy breaches. The intense popularization of Internet and the vast germination of web services that facilitates the participatory information sharing, users likely tend to share personal information which may lead to lethal causes. Social media use has become so pervasive communication media that help connect people and stay in touch beyond boundaries. It is becoming progressively more obvious that social networks have become a part of people s lives. To check status updates from the family and friends, tablet and smart phone are used by the young generation. Young people are becoming more socially capable due to social networking sites. With the adoration of sharing, Facebook has stood out as the most famous SNSs in the world where people expend time for hours. Some people on internet sites carry out dreadful acts and screen themselves behind the secrecy provided by the internet. Young people being unaware of reading the privacy policy of different websites, most of the times unknowingly reveal their personal information. If the young people fail to read the policies then it may cause risk of disclosing individual s personal information which is a cybercrime such as an identity theft. Facebook has helped a lot to create lots of different source of entertainment and informational media for personal as well as business use around the globe. It is also available in various languages and country thus involving people from all over the globe and connecting people of various dialects together as it provides translation feature. In the past, there was a buzz regarding the privacy settings of Facebook as it was very complicated but later they have simplified it for better understanding and easy access to common people. Due to lack of knowledge and understanding of privacy features of Facebook, people make many mistakes. Another important thin which should be controlled is the availability of the personal information which should be prevented d from leakage as it may reveal personal information of an individual in the form of videos, images or any data. So the information should be precise else it may lose control on the information once it is let out on internet. Facebook has provided an ease of uploading and sharing photos online in an instant. If the individual is not identified by the photo tags, then the face of an individual can be identified through the use of the facial recognition software and publicly available information which identifies the person on the photo. Since the social networking sites provides us the ease and fulfills our needs they have become the integral part of our life who provides social needs such as information sharing, social interaction and communication. Because of such an ease more people are reliable on online social network where they place their images, personal information and videos without giving a second thought. These records placed on social sites can be used for malicious purpose as it becomes a permanent record. For example, any photo posted on the site may lead a connection to some mafia world which may cause threat to someone. Privacy protection over OSNs has become an important issue as many users are careless while posting the contents of the photo which may cause far reaching effects. Facebook has feature of photo tagging which is of prime concern as it makes individual involve other person by tagging individuals and make them involve in the photo posting activity. This is initiated by tagging photos of All rights Reserved 911

2 individual who are present in the photo and thus inviting them to be active part of it. Users may even post the details or any information of the individual without their involvement and consent. The situation may be brought out due to proper tools and designs along with the lack of experience and awareness in users. This paper proposes a system based on new consent, which approaches to achieve privacy and efficiency at the same time. The local train data is formed by setting individuals private photo set so as to train the data and make individual learn the local training results. Once this result is achieved then global knowledge can be formed by exchanging the data among the users thus expanding the knowledge of the users. Later, the knowledge can be expanded and can be used as reference by the users. At last the information can be shared among various users and thus consensus can be reached through it. II. RELATED WORK Security and privacy in social network is now becoming an important research area nowadays. When a user uploads information in OSN they have a scope in mind and the privacy involves keeping that information s within the intended scope. Scope can be defined as size of the audience, extent of usage allowed, and duration of the content. Privacy is breached when information is moved beyond this scope. Case studies show that most users do not change their default privacy settings provided by the OSNs there by creating privacy issues. Current OSNS demands user to be system and policy administers for regulating their data, where users can restrict data sharing to a specific set of trusted users. In literature [6, 7, 8, 9], several proposals of an access control scheme for OSNs have been introduced. But most of them were based on the property of trust. For example, Carminative et al. introduced a trust-based access control mechanism, which allows the specification of access rules for online resources where authorized users are denoted in terms of the relationship type, depth, and trust level between users in OSNs. They also proposed a semi-decentralized discretionary access control system and an enforcement mechanism for controlled sharing of information in OSNs. Fong et al. Proposed an access control model that deals with the access control mechanism implemented in Facebook. Gates described a new method where access control was based on relationship which is a new security paradigm that addresses the requirements of the Web 2.0. Then, Fong recently formulated a paradigm called a Relationship-Based Access Control (ReBAC) where, the authorization decisions was based on the relationships between the resource owner and the resource accessor in an OSN. However, these works couldn t accommodate privacy control requirements with respect to the data sharing in OSNs. Several recent works in access control mechanism recognized the need of joint management for data sharing, in OSNs, especially in the area of photo sharing. Squicciarini et al. Proposed a solution for privacy management for photo sharing in OSNs. In this work they considered the privacy control of a content that is co-owned by multiple users in an OSN, where each co-owner may separately specify his/her own privacy preference for the shared content. The Clarke-Tax mechanism was adopted to provide the collective enforcement in the shared content. Evaluation of the scheme was done by applying Game theory. However, the drawback of this solution is the usability issue and they do not accommodate all stakeholders privacy preferences. Hongxin Hu et.al, proposes a simple but flexible mechanism for collaborative management of shared data in OSNs associated with multiple users. Even though they addressed multiparty access control issues, chances of privacy risk and data sharing loss are high due to a simple conflict resolution strategy. In contrast, in this work an effective conflict resolution solution is introduced, which makes a tradeoff between privacy protection and data sharing by considering the privacy concerns from multiple associated users.. III. PROPOSED SYSTEM To propose a facial recognition system for preserving privacy of photo sharing that can recognize everyone in the photo which enables each person in a photo is alert of the posting action and participate in the decision making while posting the photo.. IV. SYSTEM ARCHITECTURE A mechanism has been designed to make users aware of the posting activity and make them actively take part in the photo posting and decision making paradigm for which a facial recognition (FR) system is recommended which can recognize everyone present in the photo. If more privacy setting is done then it may limit the number of photos which will be utilized as the training set for FR system. In order to overcome this problem and for training set for FR system we would utilize the private photos of users which would differentiate the photo co-owners without affecting their privacy. A distributed consensus based method is developed which would protect the private training set and even reduce the computational complexity. Our contributions to this work when compared with previous work are mentioned below: We can find the potential owners of shared photos automatically even when the use of generated tags is kept as an option in our paper. Private photos in a privacy-preserving manner and social contexts to derive a personal FR engine for any Particular user is proposed in our All rights Reserved 912

3 We propose a consensus-based method to achieve privacy and efficiency. Fig.1 System Architecture System Features: photo privacy: Users care about privacy are unlikely to put photos online. Perhaps it is exactly those people who really want to have a photo privacy protection scheme. To break this dilemma, we propose a privacy-preserving distributed collaborative training system as our FR engine. In our system, we ask each of our users to establish a private photo set of their own. We use these private photos to build personal FR engines based on the specific social context and promise that during FR training, only the discriminating rules are revealed but nothing else With the training data (private photo sets) distributed among users, this problem could be formulated as a typical secure multi-party computation problem. Intuitively, we may apply cryptographic technique to protect the private photos, but the computational and communication cost may pose a serious problem for a large OSN. Social network: Study the statistics of photo sharing on social networks and propose a three realms model: a social realm, in which identities are entities, and friendship a relation; second, a visual sensory realm, of which faces are entities, and cooccurrence in images a relation; and third, a physical realm, in which bodies belong, with physical proximity being a relation. They show that any two realms are highly correlated. Given information in one realm, we can give a good estimation of the relationship of the other realm. Stone et al., for the first time, propose to use the contextual information in the social realm and co photo relationship to do automatic FR. They define a pair wise conditional random field (CRF) model to find the optimal joint labeling by maximizing the conditional density. Specifically, they use the existing labeled photos as the training samples and combine the photo co-occurrence statistics and baseline FR score to improve the accuracy of face annotation. discuss the difference between the traditional FR system and the FR system that is designed specifically for OSNs. They point out that a customized FR system for each user is expected to be much more accurate in his/her own photo collections. social networks such as Face book. Unfortunately, careless photo posting may reveal privacy of individuals in a posted photo. To curb the privacy leakage, we proposed to enable individuals potentially in a photo to give the permissions before posting a co-photo. We designed a privacy-preserving FR system to identify individuals in a co-photo. Friend list: Basically, in our proposed one-against-one strategy a user needs to establish classifiers between self, friend and friend, friend also known as the two loops in Algorithm. 2. During the first loop, there is no privacy concerns of Alice s friend list because friendship graph is undirected. However, in the second loop, Alice need to coordinate all her friends to build classifiers between them. According to our protocol, her friends only communicate with her and they have no idea of what they are computing for. Friend list could also be revealed during the classifier reuse stage. For example, suppose Alice want to find ubt between Bob and Tom, which has already been computed by Bob. Alice will first query user k All rights Reserved 913

4 see if auk has already been computed. If this query is made in plaintext, Bob immediately knows Alice and Bob are friends. To address this problem, Alice will first make a list for desired classifiers use private set operations in [10] to query against her neighbors classifiers lists one by one. Classifiers in the intersection part will be reused. Notice that even with this protection, mutual friends between Alice and Bob are still revealed to Bob, this is the trade-off we made for classifiers reuse. Actually, OSNs like Face book shows mutual friends anyway and there is no such privacy setting as hide mutual friends Collaborative Learning: To break this dilemma, we propose a privacy-preserving distributed collaborative training system as our FR engine. In our system, we ask each of our users to establish a private photo set of their own. We use these private photos to build personal FR engines based on the specific social context and promise that during FR training, only the discriminating rules are revealed but nothing else. propose to use multiple personal FR engines to work collaboratively to improve the recognition ratio. Specifically, they use the social context to select the suitable FR engines that contain the identity of the queried face image with high probability This data isolation property is the essence of our secure collaborative learning model and the detailed security analysis. V. RELEVANT MATHEMATICS ASSOCIATED WITH THE PROJECT Let S is the Whole System Consists: S = U,SP,TS,PP,PF. 1.U is the set of number users. U=U1,U2...Un. 2.SP is the set of special policy. SP=SP1,SP2...SPn. 3.TS is set of number tranning set. TS=TS1,TS2...TSn. PF is set of numbers of post photo. PF=PF1,PF2...PFn Step 1: user interface with GUI. Step 2: user specify policy for security and privacy. SP=SP1,SP2...SPn Step 3:user use training set for posting a photo. TS=TS1,TS2...TSn. Step 4:After getting permission post a photo. PF=PF1,PF2...PFn. Output: we get a secure photo posting mechanism. VI. All rights Reserved 914

5 @IJAERD-2017, All rights Reserved 915

6 @IJAERD-2017, All rights Reserved 916

7 VII. Conclusion and Future Work Photograph sharing is a standout amongst the most prevalent elements in online informal organizations, for example, Facebook. Lamentably, imprudent photograph posting may uncover security of people in a posted photograph. To control the security spillage, we proposed to empower people possibly in a photograph to give the consents before posting a co-photograph. We planned a security safeguarding FR framework to recognize people in a co-photograph. The proposed framework is highlighted with low calculation expense and privacy of the preparation set. Hypothetical examination and trials were directed to show adequacy and effectiveness of the proposed plan. We expect that our proposed plan be exceptionally helpful in ensuring clients' protection in photograph/picture sharing over online informal organizations. Then again, there dependably exist exchange off in the middle of protection and utility. For instance, in our present Android application, the co-photograph must be post with consent of all the co-proprietors. Idleness presented in this procedure will enormously affect client experience of OSNs. Moreover, neighborhood FR preparing will deplete battery rapidly. Our future work could be the way to move the proposed preparing plans to individual mists like Drop box and/or icloud. VIII. References [1] A. Besmer and H. Richter Lipford. Moving beyond untagging: photo privacy in a tagged world. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, CHI 10, pages , New York, NY, USA, ACM. [2] B. Carminati, E. Ferrari, and A. Perego. Rule-based access control for social networks. In R. Meersman, Z. Tari, and P. Herrero, editors, On the Move to Meaningful Internet Systems OTM. [3] K. Choi, H. Byun, and K.-A. Toh. A collaborative face recognition framework on a social network platform. In Automatic Face Gesture Recognition, FG 08. 8th IEEE International Conference on, pages 1 6, [4] N. Mavridis, W. Kazmi, and P. Toulis. Friends with faces: How social networks can enhance face recognition and vice versa. In Computational Social Network Analysis, Computer Communications and Networks, pages Springer London, [5]A. C. Squicciarini, M. Shehab, and F. Paci. Collective privacy management in social networks. In Proceedings of the 18th International Conference on World Wide Web, WWW 09, pages , New York, NY, USA, ACM. [6] K. Choi, H. Byun, and K.-A. Toh. A collaborative face recognition framework on a social network platform. In Automatic Face Gesture Recognition, FG 08. 8th IEEE International Conference on, pages 1 6, [7] K.-B. Duan and S. S. Keerthi. Which is the best multiclass svm method? an empirical study. In Proceedings of the 6th international conference on Multiple Classifier Systems, MCS 05, pages , Berlin, Heidelberg, Springer-Verlag. [8] P. A. Forero, A. Cano, and G. B. Giannakis. Consensus-based distributed support vector machines. J. Mach. Learn. Res., 99: , August All rights Reserved 917