Talson/mfv-openvino-ir-overflow

MFV — OpenVINO IR model file (.xml + .bin): offset+size overflow → OOB read + shape_size overflow

Target format (huntr): OpenVINO ($1500 tier, "Model File Formats") Affected project: openvinotoolkit/openvino — Intel OpenVINO Toolkit (~7.8k stars, active development) Class: CWE-190 Integer Overflow → CWE-125 Out-of-bounds Read — attacker-controlled offset and size attributes from the .xml model file overflow when added together, bypassing a bounds check. The resulting pointer computation goes out of bounds of the .bin weights buffer. Additionally, shape_size uses unsafe multiplication (safe version exists but is not used in the deserializer). Status: TOOL-VERIFIED under AddressSanitizer (SEGV READ + heap-buffer-overflow READ). 2026-06-12.

---

Threat model (why this is in MFV scope)

OpenVINO IR (Intermediate Representation) models consist of:

• .xml file: layer graph topology with tensor shapes, offsets, and sizes
• .bin file: binary weight data

The standard load path is:

ov::Core core;
auto model = core.read_model("model.xml", "model.bin");
auto compiled = core.compile_model(model, "CPU");
auto infer_request = compiled.create_infer_request();

The .xml file is fully attacker-controlled. It specifies offset and size attributes on <data> elements that tell the deserializer where to read weight data from the .bin buffer. Loading an untrusted .xml + .bin pair causes OOB memory access during model deserialization.

---

Summary of findings

#	Bug	Primitive	Function / line	Trigger	Verified
1	offset + size overflow in bounds check	OOB READ (SEGV)	xml_deserialize_util.cpp:895	offset+size attrs in XML	✅ ASAN
2	Same overflow, string tensor path	heap-buffer-overflow READ	xml_deserialize_util.cpp:828	offset+size attrs in XML	✅ ASAN
3	shape_size unsafe multiplication	validation bypass	xml_deserialize_util.cpp:904	shape attr in XML	✅ (logic)
4	Same overflow in preprocessing	OOB READ	input_model.cpp:136	mean offset+size in XML	same pattern

Root cause: arithmetic on attacker-controlled XML attributes without overflow checks, despite OpenVINO having safe arithmetic functions (mul_overflow, shape_size_safe) available but unused in the IR deserializer.

---

BUG 1 — offset+size integer overflow → OOB read (main constant path)

Root Cause

xml_deserialize_util.cpp:893-897 (OpenVINO @ 7cf8606, 2026-06-12):

const auto size = static_cast<size_t>(pugixml::get_uint64_attr(dn, "size"));
const auto offset = static_cast<size_t>(pugixml::get_uint64_attr(dn, "offset"));
OPENVINO_ASSERT(m_weights->size() >= offset + size, "Incorrect weights in bin file!");

char* data = m_weights->get_ptr<char>() + offset;

Both offset and size are attacker-controlled uint64_t values from the XML <data> element. The bounds check at line 895 computes offset + size which can overflow size_t to a small value, causing the assertion to pass.

Example: offset = 0xFFFFFFFFFFFFFF00, size = 0x200

• offset + size = 0x100 (256) — overflows!
• m_weights->size() = 1024 >= 256 → check passes
• data = weights_ptr + 0xFFFFFFFFFFFFFF00 → points ~18 EB past the buffer

ASAN Evidence

==ERROR: AddressSanitizer: SEGV on unknown address 0x7cafdb9dff80
  (pc 0x55c807f09669 bp 0x7ffe8a8e34d0 sp 0x7ffe8a8e3420 T0)
The signal is caused by a READ memory access.
    #0 test_offset_size_overflow()  harness_ir.cpp:96

(full log: findings/openvino_evidence/offset_overflow_segv.txt)

---

BUG 2 — Same overflow in string tensor path

xml_deserialize_util.cpp:819-830:

size_t offset = static_cast<size_t>(pugixml::get_uint64_attr(dn, "offset"));
// ...
if (m_weights->size() < offset + size)         // ← SAME overflow bug
    OPENVINO_THROW("Incorrect weights in bin file!");
char* data = m_weights->get_ptr<char>() + offset;
auto buffer = ...unpack_string_tensor(data, size);  // reads 'size' bytes from OOB

This path handles string-type tensor data. With a valid-looking offset (within the buffer) and a size that causes offset + size to wrap, the check passes but unpack_string_tensor reads size bytes from near-end-of-buffer → heap-buffer-overflow READ.

ASAN Evidence

==ERROR: AddressSanitizer: heap-buffer-overflow on address 0x7d46d69e0485
READ of size 1 at 0x7d46d69e0485 thread T0
    #0 test_offset_size_overflow_variant2()  harness_ir.cpp:133

0x7d46d69e0485 is located 5 bytes after 1024-byte region [0x7d46d69e0080,0x7d46d69e0480)

(full log: findings/openvino_evidence/offset_overflow_heap_oob.txt)

---

BUG 3 — shape_size unsafe multiplication (safe version exists but unused)

xml_deserialize_util.cpp:904:

if (size < ((ov::shape_size(shape) * el_type.bitwidth() + 7) >> 3)) {
    OPENVINO_THROW("Attribute and shape size are inconsistent...");
}

shape_size (defined at shape.hpp:87-95) uses std::accumulate with std::multiplies — no overflow check:

// shape.hpp:92-95 — THE UNSAFE VERSION
return std::accumulate(start_dim, end_dim,
                       typename ...:value_type{1},
                       std::multiplies<typename ...:value_type>());

OpenVINO has a safe version at shape_util.cpp:72-80:

// shape_util.cpp:72-80 — THE SAFE VERSION (NOT USED IN DESERIALIZER)
std::optional<size_t> shape_size_safe(const Shape& shape) {
    size_t size = 1;
    for (auto first = shape.cbegin(), last = shape.cend(); first != last; ++first) {
        if (mul_overflow(size, *first, size)) {    // uses __builtin_mul_overflow
            return std::nullopt;
        }
    }
    return std::make_optional(size);
}

With crafted shape dims like [2, 2, 2^62]:

• shape_size() overflows to 0
• 0 * bitwidth + 7 >> 3 = 0
• The check size < 0 fails (any size ≥ 0) → validation passes
• A Constant node is created with a shape implying 2^65 elements but only size bytes of data
• Any operation iterating shape dimensions reads past the buffer

Evidence

shape_size() = 0 (overflowed from true value > 2^64)
Validation PASSED: xml_size (1024) >= overflowed check (0)
Shape implies 2^65 elements but buffer is only 1024 bytes.

(full log: findings/openvino_evidence/shape_size_overflow.txt)

---

BUG 4 — Same offset+size overflow in preprocessing

input_model.cpp:136:

if (const_offset + const_size > weights->size()) {
    OPENVINO_THROW("mean value offset and size are out of weights size range");
}

Same pattern: const_offset and const_size from XML preprocessing <mean> element, addition can overflow.

---

Inconsistent hardening assessment

OpenVINO demonstrates inconsistent use of safe arithmetic:

Component	Function	Safe?	Notes
shape_util.cpp	shape_size_safe	✅	Uses mul_overflow
memory_util.cpp	get_memory_size_safe	✅	Uses mul_overflow
common_util.hpp	mul_overflow	✅	Uses __builtin_mul_overflow
runtime/tensor.cpp	allocation	✅	Uses get_memory_size_safe
xml_deserialize_util.cpp:895	bounds check	❌	Plain addition, no overflow check
xml_deserialize_util.cpp:828	bounds check	❌	Plain addition, no overflow check
xml_deserialize_util.cpp:904	shape validation	❌	Uses shape_size not shape_size_safe
input_model.cpp:136	bounds check	❌	Plain addition, no overflow check

The safe functions exist and are used in other code paths — the IR deserializer simply doesn't use them.

---

Affected versions

• openvinotoolkit/openvino @ HEAD (7cf8606, 2026-06-12): AFFECTED.
• All versions using the current XmlDeserializer::on_adapter implementation.
• The Python bindings (openvino pip package) that call read_model are also affected.

---

Reproduction

# Build harness with ASAN:
g++ -std=c++17 -fsanitize=address -g -O0 -o harness_ir harness_ir.cpp

# Test 1: offset+size overflow → SEGV (huge offset)
./harness_ir

# Test 2: offset+size overflow → heap-buffer-overflow (valid offset, huge size)
./harness_ir variant2

# Test 3: shape_size overflow (validation bypass)
./harness_ir shape

Build: poc/mfv_openvino_ir.cpp Build flags: g++ -std=c++17 -fsanitize=address -g -O0

---

Remediation

1. BUG 1+2+4: Replace plain offset + size with overflow-checked addition:

   size_t sum;
   OPENVINO_ASSERT(!__builtin_add_overflow(offset, size, &sum) && m_weights->size() >= sum,
                   "Incorrect weights in bin file!");
   

2. BUG 3: Use shape_size_safe instead of shape_size:

   auto maybe_shape_size = ov::util::shape_size_safe(ov::Shape(shape.begin(), shape.end()));
   OPENVINO_ASSERT(maybe_shape_size.has_value(), "Shape dimensions overflow");
   if (size < ((maybe_shape_size.value() * el_type.bitwidth() + 7) >> 3)) {
       OPENVINO_THROW("...");
   }
   

3. General: Audit all XML-derived arithmetic in the IR frontend for consistent use of safe functions.

---

Novelty / dedup

• No CVE found for integer overflow in OpenVINO's IR XML deserializer offset+size handling.
• No prior huntr disclosure for OpenVINO IR format found.
• OpenVINO has received prior security fixes (CVE-2024-* series) but none for this specific pattern.
• Dup risk: low-medium. The inconsistent safe/unsafe pattern suggests this was overlooked.

Suggested CVSS

AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:H → 7.1 (local file, user loads model; OOB read → information disclosure + crash). Note: this is OOB READ not WRITE — exploitability for code execution is lower than the WRITE bugs in other targets, but information disclosure (memory contents leaked through model outputs) is possible.