FHE programs have precision bugs random testing can't find — here's an adversarial search tool that does

FHE has a precision-testing problem, and random testing misses it If you compile an ML model to run under Fully Homomorphic Encryption, the encrypted and plaintext versions should give the same answer on every input. Under CKKS — the scheme most FHE ML deployments use — they usually do. But CKKS is approximate : noise accumulates across multiplications, and on specific inputs it can push the decrypted output far from the plaintext result. In one worked example from the patent specification behin