How we do it?

Bulletproof AI continuously monitors the protected system, analyses inputs and outputs and verifies the security, fairness and robustness of the system against many types of AI attacks or unintentional bias. Using the same methodology, we also shield traditional statistical models and rule-based systems from AI-enabled attacks or other manipulation.

Bulletproof AI platform


Finance & Fintech

Finance and Fintech companies have been using AI, machine learning, statistical decision making and expert systems in order to provide secure and convenient services to their customers. The protection of automated decision-making is especially vital in scenarios lacking humans in the loop. Bulletproof AI supports its financial sector customers in protecting their existing:

  • credit risk management and instant credit systems
  • fraud detection & prevention
  • anti-money laundering systems
  • adaptive and rule-based authentication & authorization

Bulletproof AI monitors and constantly probes the behavior of the protected system, recognizes potentially evasive, artificial or manipulative behavior and provides testing and training data necessary for system hardening against the detected attacks.

Our customers can use Bulletproof AI to prevent novel fraud scenarios that may arise due to business changes associated with PSD2 regulation and the introduction of 3D Secure 2 and Strong Customer Authentication standards.

Secure Authentication

With business applications progressively migrating to the software-as-a-service model, proper user authentication is a key element of information security posture. Phishing attacks, spear phishing and abuse of stolen credentials are the most common attacks against SaaS systems.

In order to strengthen password-based authentication, and to complement the now-mandatory second factor, many services use behavioral biometry for reliable user authentication by means of their behavior - keystroke dynamics, mouse movements, swipe gesture usage and other user-specific information. The authentication decision is typically taken by an adaptive, machine learning-based model for each user. Bulletproof AI can perform security validation of such models, detect attempts to circumvent the biometric authentication and help prevent large-scale account take-over campaigns or sophisticated spear phishing attempts.

Products & Solutions

Security Assessment

Bulletproof AI can be used in a one-shot mode to deliver an instantaneous security assessment of the system in gray-box and black-box settings. The outcome of testing can be used for system re-training, for machine learning model hardening or for robust feature engineering.

Security Monitoring

Security monitoring provides ongoing protection of the system by probing its resistance against innovative attacks and at the same time analyzing the queries of actual system users for sign of confidentiality attacks, evasion or strategic behavior.

Fairness Assessment

Fairness assessment analyzes the model and discovers any instances, where the lack of data or bias in feature selection, may have biased the model response. The assessment includes an analysis of the model's past performance extended by hypothetical scenarios generated by Bulletproof AI.

Fairness Monitoring

Fairness monitoring extends fairness assessment by constantly actively probing the model with hypothetical scenarios based on model's response to actual requests. It also analyzes the responses to production queries in order to discover unexpected bias.

Model Pre-Deployment Validation

The Bulletproof AI solution can easily be deployed as part of the model release pipeline. When a new model is released, it can be assessed from a security and fairness perspective in order to ensure proper behavior.


Besides the delivery of our product, Bulletproof AI also offers expertise in model hardening and improvement as a follow-up to assessment or monitoring delivery.

Our team

The Bulletproof AI s.r.o. team is based in Prague and Brussels. We have created Bulletproof AI with 12 years of research and industry experience in security and machine learning. Research team members have authored or co-authored hundreds of patents, journal articles and conference papers in the field of machine learning and security. Our previous startup, Cognitive Security, was acquired by Cisco Systems in 2013 and has grown to protect more than 25 million of users worldwide from advanced malware threats using machine learning.