Research

Research seriesL3algorithms

Homomorphic Encryption and Confidential AI

Fully homomorphic encryption computes directly on ciphertext, so a model you do not trust can run inference on a prompt it never sees in the clear — at a real, quantifiable performance tax. This series builds FHE from the noise-growth problem and bootstrapping through the scheme families, private neural-network inference, and an honest comparison with trusted hardware and multi-party computation. Grounded in Gentry, BGV, and CKKS.

Murali Chillakuru·5 articles
  1. 1
    Computing on Ciphertext: The FHE Promise, Noise Growth, and Why Bootstrapping Is the Central Idea

    Fully homomorphic encryption lets you compute on data while it stays encrypted. The obstacle is noise that grows with every operation; the breakthrough is bootstrapping, which refreshes it.

  2. 2
    The Scheme Families: BGV/BFV Exact Integers versus CKKS Approximate Reals

    Homomorphic schemes split by the numbers they encrypt: BGV and BFV do exact integer arithmetic; CKKS does approximate real arithmetic. The choice follows the workload.

  3. 3
    Bootstrapping and Its Cost: Refreshing Noise and the Parameter, Security, Performance Triangle

    Bootstrapping makes FHE unbounded, but it is the dominant cost. Its price is set by a three-way tension between security, performance, and how much computation you can do between refreshes.

  4. 4
    Private Inference on Neural Networks: Approximating Non-Linearities Under FHE

    The linear layers of a network are natural under homomorphic encryption; the non-linear activations are the hard part, and how you approximate them decides what private inference can do.

  5. 5
    FHE versus TEEs versus MPC: An Honest Comparison for Confidential LLM Serving

    Three roads lead to inference that hides the prompt: homomorphic encryption, trusted hardware, and multi-party computation. They differ most in where trust lives and what it costs.