- The paper introduces Index-of-Max (IoM) hashing, a ranking-based LSH technique transforming biometric features into secure, discrete codes for cancelable biometrics.
- Experimental results on benchmark datasets demonstrate favorable accuracy and robustness against various attacks, including brute-force and ARM, while maintaining key cancelable biometrics criteria.
- IoM hashing offers practical implications for biometric cybersecurity, potentially integrating with primitives like Fuzzy Vaults and applying to diverse identity authentication scenarios.
Ranking Based Locality Sensitive Hashing Enabled Cancelable Biometrics: Index-of-Max Hashing
The paper introduces a novel approach for biometric template protection, leveraging a two-factor cancelable biometrics strategy called "Index-of-Max" (IoM) hashing. The primary aim is to address concerns related to the security and privacy of biometric templates, particularly when these templates are prone to theft or compromise. IoM hashing employs externally generated random parameters to convert real-valued biometric feature vectors into discrete index-based hashed codes, which are derived from ranking-based locality sensitive hashing (LSH).
The authors outline two specific implementations of IoM hashing: Gaussian Random Projection-based hashing and Uniformly Random Permutation-based hashing. These approaches are designed to provide robust concealment of biometric data, support template non-invertibility, and maintain performance in scenarios involving biometric feature variations. Additionally, IoM hashing ensures scale invariance, which is vital during the matching and feature alignment processes.
Experimental results using benchmark fingerprint databases like FVC2002 and FVC2004 reveal favorable accuracy performance. The methodology meets essential criteria for cancelable biometrics, including non-invertibility, revocability, unlinkability, and performance preservation after transformation. The authors also conduct comprehensive analyses of the security and privacy parameters of IoM hashing, demonstrating its resilience against established and emergent security attacks, such as brute-force, Attack via Record Multiplicity (ARM), false accept, and birthday attacks.
Key Features and Results
- Biometric Feature Protection: IoM hashing uses ranking-based LSH to hash biometric feature vectors into a discrete index form, ensuring irreversibility and robustness against inversion attacks.
- Template Revocability: If a biometric template is compromised, IoM hashing allows for easy revocation and regeneration, ensuring the security and privacy of biometric data.
- Experimental Findings: Favorable accuracy results were recorded on benchmark datasets, with IoM hashing demonstrating strong concealment and resistance against various attack models.
- Security Analysis: The paper highlights the robustness of IoM hashing against challenging security threats, thereby building confidence in its revocability, unlinkability, and resistance to common biometric attacks.
Implications and Future Work
The IoM hashing scheme presents several practical implications for the field of cybersecurity within biometrics. Its capability to effectively protect biometric templates from unauthorized access while maintaining high accuracy levels creates beneficial avenues for application in systems where data security is paramount.
Furthermore, IoM hashing might form the foundation for future research in integrating it with biometric cryptosystem primitives, like Fuzzy Vault and Fuzzy Commitment, enhancing privacy-preserving capabilities. Exploration into its utility in varied identity authentication scenarios and adaptive application to multi-modal biometric systems also offers promising prospects.
In conclusion, while the work done here reflects considerable advancement in biometric template security, continued refinement of IoM hashing - particularly in terms of complexity and application scope - is essential to maximize its benefits in real-world implementations.