Explore our new Cybersecurity Terms Glossary, explained by our experts.

View the Glossary View the Glossary
PRIVIA

Cybersecurity Terms Glossary

What Is Federated Learning Security?

Federated learning trains a shared model without pooling the data, but the updates participants exchange can leak their training records and can be crafted to poison the global model.

Illustration for the cybersecurity term Federated Learning Security
Home / Blog / Cybersecurity Terms / What Is Federated Learning Security?
17 November 2026

What Is Federated Learning Security?

What Is Federated Learning Security?

Federated learning trains a shared model across many parties without any of them sending their raw data anywhere. Each participant trains locally on its own records and sends only a model update; a server aggregates those updates into a new global model and redistributes it. Google deployed the approach for mobile keyboard prediction in 2017, and it has since become the standard proposal whenever data cannot legally or commercially be pooled—between hospitals, between banks sharing fraud signals, or across devices.

Two Shapes, Two Threat Models

Cross-device federation involves thousands or millions of phones and sensors, most of them untrusted, each contributing a tiny amount. Cross-silo federation involves a handful of institutions with their own infrastructure, contracts, and legal teams. The security question differs accordingly: at device scale the realistic threat is a population of malicious clients, while in a silo arrangement the questions are whether a partner can reconstruct your data from your updates and whether the aggregating party is trustworthy.

Updates Leak More Than Expected

The central assumption—that gradients reveal nothing about the data—does not hold. Work published in 2019 under the title Deep Leakage from Gradients showed that original training images and labels could be reconstructed pixel by pixel from the gradients of a small batch. Later research extended reconstruction to larger batches and to text, and showed that a malicious server can modify the model it distributes to make reconstruction easier. Related attacks infer whether a specific record was in a participant’s dataset, which is the membership inference problem arriving through a side door, or infer properties of a participant’s population, such as the demographic mix of a hospital’s patients.

Poisoning From Inside the Federation

Because participants train locally, nobody inspects their data or their process. A malicious client can send crafted updates to degrade the global model or to implant a backdoor that fires on a chosen trigger while leaving normal accuracy untouched—a scenario demonstrated in How to Backdoor Federated Learning in 2020. Sybil attacks make it worse: in a cross-device setting, one attacker controlling many fake clients can outweigh honest contributions. This is ordinary data poisoning, but with the defender denied the usual remedy of inspecting the training set.

Controls That Address Each Risk

The UK Data Protection Angle

Federated learning is frequently presented as a way to avoid data protection obligations, and that claim needs care. Model updates derived from personal data may themselves be personal data where reconstruction is feasible, so the ICO’s identifiability test applies to the updates, not just to the raw records. The approach is nonetheless strong evidence of data protection by design under Article 25 and of data minimisation, and the ICO treats federated analytics as a privacy-enhancing technology in its guidance. In practice the arrangement also needs clear allocation of controller and processor roles across participants, a joint controller agreement where decisions are shared, and a documented security assessment of the aggregation protocol. In health research the comparable UK pattern is the secure data environment, where analysts come to the data rather than the data moving; federated learning fits the same policy direction. At Privia Security, our Cyber Risk Analysis Services assess distributed training architectures before partners commit to them.

FAQ – Frequently Asked Questions

Does Federated Learning Mean Data Never Leaves Our Premises?

The raw records do not, which is the main benefit. Model updates do leave, and those updates can leak information about the data that produced them, sometimes enough to reconstruct individual examples. Treat the updates as a controlled export, protect them with secure aggregation and differential privacy, and document that analysis rather than relying on the raw-data argument alone.

How Do We Stop a Malicious Participant?

Combine prevention with detection. Authenticate and, where possible, attest clients so fake participants are expensive to create; clip and bound each update so no single contributor can dominate a round; use robust aggregation to discard outliers; and monitor contributions across rounds for participants who consistently pull the model in an unusual direction. None of these is sufficient alone against a determined, patient attacker.

Is Secure Aggregation Enough on Its Own?

No. It prevents the server from seeing any individual update, which closes the most direct reconstruction path, but the aggregate itself still carries information, and a colluding majority of clients can isolate a victim’s contribution. Pair it with differential privacy for a formal bound, and with robust aggregation to address poisoning, which secure aggregation does nothing to prevent.

When Is Federated Learning the Right Choice?

When the data genuinely cannot be centralised for legal, contractual, or volume reasons, and the participants share an interest in one model. If you could lawfully pool the data in a single controlled environment, that is usually simpler, cheaper, and easier to secure. Federation adds a distributed protocol, several new attack surfaces, and significant engineering overhead.

Related Terms

You May Be Interested In These

What Is IEC 61850?

Cybersecurity Terms

17 November 2026

What Is IEC 61850?

Read More
What Is Whaling?

Cybersecurity Terms

17 November 2026

What Is Whaling?

Read More
What Is Trivy?

Cybersecurity Terms

17 November 2026

What Is Trivy?

Read More