ABSTRAT:
Cloud computing has achieved maturity, and there is a heterogeneous group of providers and cloud-based services. However, significant attention remains focused on security concerns. In many cases, security and privacy issues are a significant barrier to user acceptance of cloud computing systems and the advantages these offer with respect to previous systems. Biometric technologies are becoming the key aspect of a wide range of secure identification and personal verification solutions, but in a cloud computing environment they present some problems related to the management of biometric data, due to privacy regulations and the need to trust cloud providers. To overcome those problems in this paper, we propose a crypto biometric system applied to cloud computing in which no private biometric data are exposed
EXISTING SYSTEM :
the former, a binary key is directly created from the biometric data, whereas in the latter stored data contain biometric data combined with a random bi- nary sequence. The main drawback of key generation schemas is the instability of the resulting cryptographic key, which degrades recognition performance [17]. Key binding systems can protect a biometric template using a binary key, thus securing the biometric system, or they can release a cryptographic key only if the owner presents a legitimate biometric trait. In both cases a secret key that is independent of the biometric data is combined with a biometric template during Enrollment to produce helper data. In the authentication stage, acquired biometric data are used in conjunction with the stored helper data to retrieve the secret key. Error correcting codes (ECCs) are commonly employed to manage the intra-class variability of the biometric templates. One of the most extended key binding solutions is fuzzy commitment [18], already applied to fingerprints [19], face [20], and iris [21], among others. However, fuzzy commitment schemas are vulnerable to a cross-link attack described in [22]: it has been observed that if an attacker acquires two different fuzzy commitments obtained using the same (n, k, t) code, he can try to decode the binary string obtained by summing them to verify if they come from the same user. In order to address this drawback, biometric templates used in different fuzzy commitment systems must be different. This can be achieved by incorporating characteristics of a feature transformation approach
EXISTING SYSTEM DISADVANTAGES:
1.LESS ACCURACY
2. LOW EFFICIENCY
PROPOSED SYSTEM :
the templates are stored in a database but template protection is not addressed. A cloud private matching identification algorithm is proposed in [9]. Two encrypted images are compared under double encrypted conditions, from the client and from the cloud storage. Unlike our schema, this algorithm does not include a mechanism to renew the biometric templates. Finally, the schema in [9] employs cryptography to protect the templates that are stored in the cloud, but it does not consider the issue of data location. When the data are stored in the user infrastructure, information location and protection mechanisms are known in detail. In contrast, a characteristic of public cloud computing services is that the user is completely unaware of data location. This makes it impossible to ensure that national compulsory regulations are met. For example, European data protection laws may impose extra constraints on the handling and processing of data that are transferred to the USA, so the use of Amazon S3 resources to store biometric templates could infringe the law
PROPOSED SYSTEM ADVANTAGES:
1.HIGH ACCURACY
2.HIGH EFFICIENCY
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
