Incode’s new network for anonymized fraud signals boosts detection by 53% | Biometric Update

Incode’s new network for anonymized fraud signals boosts detection by 53% | Biometric Update

Incode’s new TrustGraph platform demonstrates a significant leap forward in privacy-preserving data analysis by enabling institutions to share fraud signals without exchanging underlying personal data. By utilizing secure multi-party computation and cryptographic matching, participating banks and fintechs can identify repeat fraudulent activities even when identities change. This collaborative approach allows organizations to detect up to half more fraud cases than isolated models, proving that shared intelligence enhances security while maintaining strict regulatory compliance and individual privacy. This mechanism is particularly relevant to open data principles as it challenges the traditional binary between data silos and open access. Instead of releasing raw datasets, TrustGraph offers a privacy-centric model where value is derived from aggregated insights rather than individual records. It illustrates how decentralized networks can improve global security standards without compromising user confidentiality. This approach suggests that future open data initiatives might increasingly rely on cryptographic verification methods to balance transparency with necessary data protection, fostering trust among competitors who must collaborate to combat sophisticated threats. As AI-driven fraud such as deepfakes becomes more prevalent, the necessity for shared intelligence grows urgent. No single entity can effectively combat synthetic identities alone, making networks like TrustGraph essential for industry-wide resilience. This shift implies that open data ecosystems must evolve beyond simple information sharing to include secure, privacy-preserving collaboration frameworks. Ultimately, TrustGraph highlights a viable path where organizations can openly benefit from collective learning while adhering to strict data privacy norms, setting a precedent for how sensitive information can be managed responsibly in an increasingly automated threat landscape.

Related news

• Security flaws found in top open source AI gateway — LiteLLM vulnerabilties could affect millions of users
• Agentic threat intelligence with Gemini in Google Threat Intelligence
• Hidden AI Capabilities Can Be Made Cryptographically Undetectable, NeurIPS Paper Proves
• Pillar Security Discovers 'BadEngram,' Exposing Hidden Supply-Chain Risk in Open-Weight AI Models – IT Business Net
• LankaWeb – 7th Reminder – Request for Acknowledgement of my Appeal Dated 29 July 2026 and then Status of my RTI Requests