We’re Tracking the Future of Security

Tag: Biometrics

  • Germany’s BSI Opens Call for Background-Removal Technology in New Biometric Benchmark

    Germany’s BSI Opens Call for Background-Removal Technology in New Biometric Benchmark

    Germany’s Federal Office for Information Security (BSI) is calling on developers to submit background-removal software and device-based solutions for a new benchmark focused on facial images. The BGR-PROJECT, short for Background Removal Benchmark, aims to assemble what BSI calls a “representative and technically sound selection” of current background-removal algorithms for standardized evaluation, with submissions open until November 27, 2026.

    Why background removal matters for passport photos

    Background removal separates a person from their surroundings in a photograph so the subject can be recomposited onto a plain, uniform background, as required by identity-document standards including ISO/IEC 39794-5 and ICAO Doc 9303 for machine-readable travel documents. Those specifications are designed to prevent distracting shadows, patterns or objects behind a subject’s head from degrading image quality used for biometric identity verification. BSI notes that the task sounds simple but is technically difficult: isolating exactly where a person ends and the background begins without introducing artifacts that reduce facial image quality.

    What the benchmark will measure

    Once BSI collects submissions, the agency plans to use them to build a benchmark that scores background-removal tools on accuracy and consistency, giving passport and ID-document issuers and biometric vendors a standardized way to compare implementations rather than relying on vendor claims alone.

    Sources and further reading

  • Noblis Patents Continuous Authentication System Using Biometrics and Environmental Sensors

    Noblis Patents Continuous Authentication System Using Biometrics and Environmental Sensors

    Noblis has announced a U.S. patent for an electronic access-control system designed to verify identity and environmental conditions continuously rather than relying only on a login-time check. U.S. Patent No. 12,682,086 combines biometric sensing, environmental monitoring, and machine-learning analysis, according to the research organization.

    Identity and context are evaluated together

    The described system combines facial recognition, gaze tracking, and blink detection with signals about spatial security, electromagnetic conditions, and network integrity. Those inputs contribute to a dynamic liveness score intended to identify presentation attacks such as photographs or deepfakes while checking whether the authorized person remains present. Based on configured criteria, the system can maintain access, restrict selected functions, or block access when conditions change.

    A patent is not deployment evidence

    The announcement documents patented architecture and intended capabilities; it does not by itself establish production adoption, independent performance results, or certification for a particular deployment. Security teams evaluating continuous authentication still need to consider privacy, biometric data governance, failure handling, accessibility, sensor reliability, and the operational impact of false decisions. The approach is relevant to remote and high-assurance access scenarios where a one-time credential check may not provide enough assurance throughout a session. More identity and access-control developments are tracked in the SectechMedia Technology News archive.

    Sources

  • Jumio Expands Selfie-Based Reusable Identity Service Across EMEA

    Jumio Expands Selfie-Based Reusable Identity Service Across EMEA

    Jumio has expanded its selfie.DONE reusable identity service across Europe, the Middle East and Africa, completing the company’s announced worldwide rollout. The service is intended for people who have already completed an identity check, allowing a participating organization to recognize a returning user through a new selfie rather than requesting another document scan.

    Reuse depends on consent and a fresh biometric check

    Jumio says the process links the returning selfie to a previously verified identity through its Identity Graph while applying current biometric matching, liveness analysis, and risk checks. The company describes the model as consent-based: a user can choose the reusable route when it is offered. The EMEA launch follows earlier availability in Latin America, North America, and the Asia-Pacific region.

    Deployment still requires governance controls

    Reusable identity can reduce repeated document collection, but it also increases the importance of clear consent, retention rules, revocation processes, account-recovery controls, and regional privacy compliance. Organizations should define how a reusable identity is refreshed, what happens when risk signals change, and how users can challenge an incorrect decision. The launch announcement describes a commercial service; it does not replace an independent assessment of accuracy, privacy, or regulatory fit for a particular use case. More identity-security developments are tracked in the SectechMedia Technology News archive.

    Sources

  • ICAO Pushes Digital Travel Credentials and Contactless Border Processing

    ICAO Pushes Digital Travel Credentials and Contactless Border Processing

    The International Civil Aviation Organization is urging governments and industry to accelerate digital identity and contactless border processing while preserving interoperability and security. The direction follows discussions around the ICAO Traveller Identification Programme and live airport deployments that use biometrics, automated gates and digital credentials.

    Standards connect different national systems

    Countries are moving at different speeds and operate under different legal frameworks. ICAO’s role is to provide standards, recommended practices and technical guidance that allow credentials and travel documents to be recognized across borders. The organization is developing the ICAO Digital Travel Credential and already maintains the Public Key Directory used to support verification of electronic travel documents.

    Automation can move routine checks to self-service lanes and let border officers concentrate on exceptions and higher-risk cases. It does not remove the need for trained staff. Identity proofing, relying-party acceptance, cybersecurity and data governance must work across the full chain from document issuance to border inspection.

    Deployment still requires measured rollout

    Airport and government teams should treat interoperability, privacy and operational resilience as commissioning requirements rather than later additions. Pilots need representative passenger flows, failure handling and a clear route back to manual inspection. Incremental deployment also gives authorities evidence about accessibility and error rates before scaling. SectechMedia tracks these systems in its border security coverage.

    Sources

  • NIST Age Estimation Results Shift With Operational Use Case

    NIST Age Estimation Results Shift With Operational Use Case

    NIST’s latest Face Analysis Technology Evaluation results underline why age-estimation systems cannot be ranked by a single universal score. The current round adds four algorithm submissions and reports performance across age distributions, demographic groups, image resolution and age-assurance decision thresholds.

    Rankings depend on the decision being made

    Average error can change when every age receives equal weight or when results are weighted by the number of images in the test set. Resolution testing also asks a different question: whether performance remains stable as fewer pixels are available across a face. NIST’s demographic analysis preserves the direction of error, revealing whether particular groups are estimated older or younger rather than hiding those effects inside one overall average.

    Threshold tests are especially relevant to age-restricted services because the operational concern is not simply the distance between estimated and actual age. It is whether an error moves a person across a policy boundary. The latest results therefore do not establish one best algorithm for every deployment.

    Procurement should follow the use case

    Operators should test candidate systems against their own age distribution, capture devices, lighting, image resolution and legal threshold. A model that performs well on a broad average may not be the safest choice near a particular age boundary. Human review, appeals and privacy controls remain important where an automated estimate affects access to a service. SectechMedia follows related identity developments in its access control and identity coverage.

    Sources

  • ICE Plans Nationwide Intelligence Support Network for Biometric Targeting Operations

    ICE Plans Nationwide Intelligence Support Network for Biometric Targeting Operations

    U.S. Immigration and Customs Enforcement is preparing a contracting effort to expand intelligence research support across Enforcement and Removal Operations headquarters, field areas and national targeting centers. The proposed structure, described in federal procurement records, would place cleared analysts in locations that already use biometric and biographic information for identity resolution.

    A distributed analyst network

    The planning documents call for approximately 142 intelligence research specialists across headquarters, 24 field areas and three national support centers. The Law Enforcement Support Center, National Criminal Analysis and Targeting Center and Pacific Enforcement Response Center already combine law-enforcement, immigration and identity information to generate operational leads.

    The statement of work does not say that contractor analysts will operate a new facial-recognition or fingerprint platform. It describes all-source research, intelligence-gap analysis, network analysis and operational support within an existing enforcement architecture. Reporting should therefore distinguish the proposed analyst workforce from any separate biometric technology procurement.

    Governance and oversight

    The records describe work involving classified information, law-enforcement-sensitive data and personally identifiable information. Any deployment will require strict access controls, audit logging, human oversight, retention rules and review of how identity data supports consequential decisions. The procurement notice was posted on September 18 and remained a planning action rather than proof of a completed award. SectechMedia follows similar systems in its border security coverage.

    Sources

  • UK Home Office Awards Ingenium Two-Year Biometric Testing and Assurance Contract

    UK Home Office Awards Ingenium Two-Year Biometric Testing and Assurance Contract

    Ingenium Biometric Laboratories has begun work under a two-year UK government contract to provide independent biometric testing and assurance for Home Office programs. The work covers quality assurance, performance evaluation and security testing for technologies used in identity assurance, age assessment and related services.

    Testing across defined use cases

    The published service description includes biometric algorithm assessment, adversarial detection assessment and specialist assurance activities. Testing is expected to evaluate performance for an agreed use case rather than produce a single universal score. Relevant measures may include matching performance, sample quality, age-assessment outputs and other algorithm results specified by the program.

    The contract also calls for repeatable methods, analysis of trends and errors, and practical recommendations. Ongoing assessments are intended to show how performance changes over the contract lifecycle. That is important because accuracy can vary with capture conditions, demographic composition, software revisions and the decision thresholds used by an operational service.

    Assurance is broader than headline accuracy

    Independent biometric evaluation should document datasets, environmental conditions, failure modes and the limits of any conclusion. Security testing is also necessary because a system can meet an accuracy target while remaining vulnerable to presentation attacks, poor enrollment controls or unsafe integration.

    For related design and governance considerations, see SectechMedia’s Access Control & Identity coverage. Procurement teams should map each test result to the exact workflow and risk decision it is meant to support.

    Sources

  • MojeID Adds Post-Quantum Protection to Digital Identity Logins

    MojeID Adds Post-Quantum Protection to Digital Identity Logins

    Czech digital identity service MojeID has introduced post-quantum cryptography protections for encrypted server communications and login confirmation in its mobile application. The change is intended to prepare authentication services for a future in which sufficiently capable quantum computers could undermine widely used public-key algorithms.

    Protection at the transport and login layers

    According to reporting published September 21, MojeID has enabled a post-quantum key-exchange option for connections to its servers. The MojeID Klíč mobile application has also added post-quantum algorithms for identity-confirmation operations in version 16.0.0. The application was developed with security technology company Wultra.

    New users receive the updated protection automatically. Existing users can update cryptographic keys through the application’s settings, with authorization by PIN or supported biometric confirmation. MojeID says further stages of its quantum-safe identity roadmap will be discussed in October. The implementation does not mean every component of the identity ecosystem has completed a post-quantum migration; it is one step in a broader transition that also involves protocols, certificates, devices and relying services.

    Operational considerations for identity teams

    Post-quantum migration should be treated as an inventory and lifecycle-management program rather than a single algorithm replacement. Organizations need to identify where cryptographic dependencies exist, determine which components can support hybrid or post-quantum mechanisms and plan key rotation without locking out users. Authentication recovery and device replacement procedures remain important because stronger cryptography does not remove account-recovery risk. SectechMedia follows related developments in cyber-physical security and identity infrastructure.

    Sources

  • NIST FRTE Update Shows Face-Matching Leaders Vary by Capture Scenario

    NIST FRTE Update Shows Face-Matching Leaders Vary by Capture Scenario

    The latest NIST Face Recognition Technology Evaluation results reinforce a practical lesson for biometric buyers: performance rankings depend heavily on the image scenario being tested. An analysis published on September 21 examines NIST’s September 1 FRTE 1:1 report, which includes new and updated submissions across visa, border, mugshot and kiosk comparisons.

    No single leaderboard tells the whole story

    Different capture environments introduce different combinations of lighting, pose, camera position, image quality and user interaction. The reported leaders therefore change from one dataset to another. Controlled visa-photo comparisons produce a very different error profile from kiosk images captured during a live border process. Several updated algorithms moved into leading groups in particular scenarios, while other established performers retained their positions elsewhere.

    The results also include demographic-performance measures. These are not interchangeable with overall matching accuracy: an algorithm may improve its headline error rate without showing the same relative strength across demographic groups. Buyers should read both sets of results and avoid presenting one benchmark score as proof of universal performance.

    Implications for procurement and acceptance testing

    A meaningful evaluation starts with the intended deployment. Teams should define enrollment image quality, live-capture conditions, user population, gallery size and whether the application is one-to-one verification or one-to-many identification. Laboratory results can narrow a vendor list, but a site-specific pilot remains necessary before operational approval. Acceptance testing should also measure failure handling and manual review, not only successful matches. More coverage of these design questions appears in SectechMedia’s identity and access-control channel.

    Sources

  • DHS Expands RIVR Tests to Deepfakes and AI-Generated Identity Documents

    DHS Expands RIVR Tests to Deepfakes and AI-Generated Identity Documents

    The U.S. Department of Homeland Security is expanding its Remote Identity Validation Rally to test how commercial identity-verification systems respond to AI-generated documents and biometric deepfakes. DHS Science and Technology announced the 2026 program on September 21, adding a dedicated deepfake-detection track alongside broader document-validation and presentation-attack testing.

    What the expanded evaluation covers

    The program is designed to examine technologies used in remote onboarding, where a person submits an identity document and a selfie or video rather than appearing at a service counter. DHS says the new evaluation will include synthetic or altered documents, face-swap video and other impersonation techniques that can be used during video calls or teleconferencing. Applications for document-validation and selfie-to-document systems are scheduled to open in October, followed by presentation-attack and deepfake-detection submissions in December.

    DHS also plans to request real-world deepfake samples and information about attack methods from organizations able to contribute threat data. That material is intended to strengthen the test dataset and make evaluations more representative of current fraud techniques. The agency has not yet published the full technical protocol, so details such as how digital injection attacks will be separated from camera-presented attacks remain open.

    Why it matters for identity programs

    Government-run comparative testing can help buyers understand where products perform consistently and where results vary by device, document or attack type. Earlier RIVR testing found substantial differences among document-validation and liveness systems. The expanded work also reflects the direction of NIST identity-proofing guidance, which calls for controls against forged media and digital injection. Organizations reviewing remote access and onboarding technology should therefore assess fraud resistance together with usability, privacy and operational fallback processes. SectechMedia tracks related developments in access control and identity technology.

    Sources