From 8a77214c8292f5f7ce94dee7b4f363b5c14d91af Mon Sep 17 00:00:00 2001
From: Val Snyder <micasnyd@cisco.com>
Date: Thu, 27 Mar 2025 14:15:48 -0400
Subject: [PATCH] Add CL_TYPE_AI_MODEL and associated file type magic
 signatures

This is just preliminary support for identifying an assortment of
different AI model files.

So far, this detects the following types:
- GGML GGUF (.gguf)
- ONNX AI (.onnx)
- TensorFlow Lite (.tflite)

Additional types to consider:
- SafeTensors (.safetensors)
- TensorFlow (.pb, .ckpt, .tfrecords)
- Keras (.keras)
- pickle (.pkl)
- numpy (.npy, .npz)
- coreml (.coreml)
- PyTorch (.pt, .pth, .bin, .mar, .pte, .pt2, .ptl)

Outside of being able to differentiate by file type, the scanner
will treat CL_TYPE_AI_MODEL the same as CL_TYPE_BINARY_DATA.
We're not adding parsers to further process these files, for now.
---
 libclamav/filetypes.c     |  1 +
 libclamav/filetypes.h     |  1 +
 libclamav/filetypes_int.h | 22 ++++++++++++++++++++++
 libclamav/scanners.c      |  1 +
 4 files changed, 25 insertions(+)

diff --git a/libclamav/filetypes.c b/libclamav/filetypes.c
index 6d81c8aa9..a31006a91 100644
--- a/libclamav/filetypes.c
+++ b/libclamav/filetypes.c
@@ -142,6 +142,7 @@ static const struct ftmap_s {
     { "CL_TYPE_ONENOTE",            CL_TYPE_ONENOTE         },
     { "CL_TYPE_PYTHON_COMPILED",    CL_TYPE_PYTHON_COMPILED },
     { "CL_TYPE_LHA_LZH",            CL_TYPE_LHA_LZH         },
+    { "CL_TYPE_AI_MODEL",           CL_TYPE_AI_MODEL        },
     { NULL,                         CL_TYPE_IGNORED         }
 };
 // clang-format on
diff --git a/libclamav/filetypes.h b/libclamav/filetypes.h
index f1677e103..a6b804870 100644
--- a/libclamav/filetypes.h
+++ b/libclamav/filetypes.h
@@ -95,6 +95,7 @@ typedef enum cli_file {
     CL_TYPE_ONENOTE,
     CL_TYPE_PYTHON_COMPILED,
     CL_TYPE_LHA_LZH,
+    CL_TYPE_AI_MODEL,
 
     /* Section for partition types */
     CL_TYPE_PART_ANY, /* unknown partition type */
diff --git a/libclamav/filetypes_int.h b/libclamav/filetypes_int.h
index c25802162..47b477d05 100644
--- a/libclamav/filetypes_int.h
+++ b/libclamav/filetypes_int.h
@@ -302,5 +302,27 @@ static const char *ftypes_int[] = {
     "1:2:2d6c7a(73|34|35)2d:LHA archive using .LZS extension:CL_TYPE_ANY:CL_TYPE_LHA_LZH:210",
     "1:2:2d706d302d:LHA archive using PMarc (.PMA) extension:CL_TYPE_ANY:CL_TYPE_LHA_LZH:210",
     "0:0:414c5a01:ALZ:CL_TYPE_ANY:CL_TYPE_ALZ:210",
+    // GGML GGUF models
+    "0:0:4747554601000000:GGUF AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    "0:0:4747554602000000:GGUF AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    "0:0:4747554603000000:GGUF AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: onnx_tool or onnx-tool
+    "1:0:08??12??6f6e6e78(2d|5f)746f6f6c:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: tf2onnx
+    "1:0:08??12??7466326f6e6e78:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: pytorch
+    "1:0:08??12??7079746f726368:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: caffe:
+    "1:0:08??12??63616666653a:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: OnnxMLTools:
+    "1:0:08??12??4f6e6e784d4c546f6f6c73:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: CNTK
+    "1:0:08??12??434e544b:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: onnx-caffe2:
+    "1:0:08??12??6f6e6e782d636166666532:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // ONNX AI model detection, looking for: onnx-caffe2:
+    "1:0:08??12??6f6e6e782d636166666532:ONNX AI Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
+    // tflite model detection
+    "0:4:54464c33:TensorFlow Lite Model File:CL_TYPE_ANY:CL_TYPE_AI_MODEL:220",
     NULL};
 #endif
diff --git a/libclamav/scanners.c b/libclamav/scanners.c
index b32eeeca0..db5b81807 100644
--- a/libclamav/scanners.c
+++ b/libclamav/scanners.c
@@ -5448,6 +5448,7 @@ cl_error_t cli_magic_scan(cli_ctx *ctx, cli_file_t type)
             perf_nested_stop(ctx, PERFT_MACHO, PERFT_SCAN);
             break;
 
+        case CL_TYPE_AI_MODEL:
         case CL_TYPE_PYTHON_COMPILED:
         case CL_TYPE_BINARY_DATA:
             ret = cli_scan_fmap(ctx, CL_TYPE_OTHER, false, NULL, AC_SCAN_VIR, NULL, NULL);