Bollwerk

Bollwerk Labs

An applied defense lab in Zurich.

We work on agentic threat detection: our own foundation models, synthetic and adversarial threat data, and agents that hold up under attack.

The four problems.

  1. Long-horizon investigation. We build environments and benchmarks for investigations that unfold over hundreds of steps.
  2. Adversarial robustness. We stage synthetic adversarial cases and red-team environments that make failure visible before deployment.
  3. Policy-constrained action. We run a policy engine that evaluates every consequential action at call time.
  4. Verifiable decisions. We record evidence lineage and replayable traces that preserve sources, policy, reasoning, and human judgment.

Agents need a bank to practice on. So we built one.

Frontier is a connected synthetic institution with customers, transactions, alerts, cases, analyst decisions, and security telemetry. We attack it with synthetic identities, credential replay, transaction laundering, and poisoned evidence.

We Built a Fake Bank ยท The Advisor Persona

We manufacture the adversarial supply.

Detection models need threats to learn from. We generate risk-relevant operations at scale, privacy-clean by construction, and compose typologies that have yet to happen from known criminal building blocks, planted as exact ground truth. Novel threats become detectable before the first real case.

Thousands of judged conversations before a real one.

Simulated environments combine personas, scenarios, mocked tools, and adversarial conversations. Each run measures the decision, evidence trail, policy compliance, and investigation path.

Training and benchmarking run on Foundry, inside the institution's own boundary.

Built in Zurich at the intersection of frontier AI and Europe's regulated institutions.

A decade supervising Swiss banks shapes the controls. Production ML systems at Moderna and Novartis shape how models are evaluated and shipped. ETH recruiting relationships keep the work close to Zurich's research community.

Selected writing

Work on the four problems.

careers@bollwerk.ai