From 9509081b1ecfe5a5e0036a8bd6e293c0f291a833 Mon Sep 17 00:00:00 2001
From: Jim Crist-Harif <jcristharif@gmail.com>
Date: Mon, 29 Sep 2025 13:56:25 -0500
Subject: [PATCH] Ensure finite values passed to SpectralEmbedding

The C++ implementation doesn't support non-finite values. Sometimes this
results in a failure-to-converge error, sometimes this results in an
illegal memory access (and downstream failures eventually leading to
potential segfaults).
---
 python/cuml/cuml/manifold/spectral_embedding.pyx | 13 ++++++++++---
 python/cuml/tests/test_spectral_embedding.py     |  9 +++++++++
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/python/cuml/cuml/manifold/spectral_embedding.pyx b/python/cuml/cuml/manifold/spectral_embedding.pyx
index 2f06702e26..3f850eabab 100644
--- a/python/cuml/cuml/manifold/spectral_embedding.pyx
+++ b/python/cuml/cuml/manifold/spectral_embedding.pyx
@@ -20,10 +20,10 @@ import scipy.sparse as sp
 from pylibraft.common.handle import Handle
 
 import cuml
-from cuml.common import input_to_cuml_array
 from cuml.common.array_descriptor import CumlArrayDescriptor
 from cuml.internals.array import CumlArray
 from cuml.internals.base import Base
+from cuml.internals.input_utils import input_to_cupy_array
 from cuml.internals.interop import (
     InteropMixin,
     UnsupportedOnGPU,
@@ -154,9 +154,10 @@ def spectral_embedding(A,
     cdef device_resources *h = <device_resources*><size_t>handle.getHandle()
 
     if affinity == "nearest_neighbors":
-        A = input_to_cuml_array(
+        A = input_to_cupy_array(
             A, order="C", check_dtype=np.float32, convert_to_dtype=cp.float32
         ).array
+        isfinite = cp.isfinite(A).all()
     elif affinity == "precomputed":
         # Coerce `A` to a canonical float32 COO sparse matrix
         if cp_sp.issparse(A):
@@ -168,6 +169,7 @@ def spectral_embedding(A,
         else:
             A = cp_sp.coo_matrix(cp.asarray(A, dtype="float32"))
         A.sum_duplicates()
+        isfinite = cp.isfinite(A.data).all()
     else:
         raise ValueError(
             f"`affinity={affinity!r}` is not supported, expected one of "
@@ -176,6 +178,11 @@ def spectral_embedding(A,
 
     n_samples, n_features = A.shape
 
+    if not isfinite:
+        raise ValueError(
+            "Input contains NaN or inf; nonfinite values are not supported"
+        )
+
     if n_samples < 2:
         raise ValueError(
             f"Found array with {n_samples} sample(s) (shape={A.shape}) while a "
@@ -220,7 +227,7 @@ def spectral_embedding(A,
             deref(h),
             config,
             make_device_matrix_view[float, int, row_major](
-                <float *><uintptr_t>A.ptr,
+                <float *><uintptr_t>A.data.ptr,
                 <int>A.shape[0],
                 <int>A.shape[1],
             ),
diff --git a/python/cuml/tests/test_spectral_embedding.py b/python/cuml/tests/test_spectral_embedding.py
index 1515d2619f..8f4dbf0851 100644
--- a/python/cuml/tests/test_spectral_embedding.py
+++ b/python/cuml/tests/test_spectral_embedding.py
@@ -232,6 +232,15 @@ def test_spectral_embedding_invalid_affinity():
         spectral_embedding(X, affinity="oops!")
 
 
+@pytest.mark.parametrize("value", [float("inf"), float("nan")])
+@pytest.mark.parametrize("affinity", ["nearest_neighbors", "precomputed"])
+def test_spectral_embedding_nonfinite(value, affinity):
+    X = np.array([[0, 1], [2, 3], [0, value]], dtype="float32")
+
+    with pytest.raises(ValueError, match="nonfinite"):
+        spectral_embedding(X, affinity=affinity)
+
+
 @pytest.mark.parametrize(
     "input_type,expected_type",
     [