From 47551b8cc10a1457f0c0f5df1fe7edd4c7d32d30 Mon Sep 17 00:00:00 2001 From: Chris Lenk Date: Wed, 25 Sep 2019 14:28:24 -0400 Subject: [PATCH] Add documentation for semantic equivalence --- docs/guide/environment.ipynb | 2 +- docs/guide/equivalence.ipynb | 1436 ++++++++++++++++++++++++++++++++++ 2 files changed, 1437 insertions(+), 1 deletion(-) create mode 100644 docs/guide/equivalence.ipynb diff --git a/docs/guide/environment.ipynb b/docs/guide/environment.ipynb index f7515a5..8d22e39 100644 --- a/docs/guide/environment.ipynb +++ b/docs/guide/environment.ipynb @@ -67,7 +67,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ diff --git a/docs/guide/equivalence.ipynb b/docs/guide/equivalence.ipynb new file mode 100644 index 0000000..9b49c2f --- /dev/null +++ b/docs/guide/equivalence.ipynb @@ -0,0 +1,1436 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "nbsphinx": "hidden" + }, + "outputs": [], + "source": [ + "# Delete this cell to re-enable tracebacks\n", + "import sys\n", + "ipython = get_ipython()\n", + "\n", + "def hide_traceback(exc_tuple=None, filename=None, tb_offset=None,\n", + " exception_only=False, running_compiled_code=False):\n", + " etype, value, tb = sys.exc_info()\n", + " return ipython._showtraceback(etype, value, ipython.InteractiveTB.get_exception_only(etype, value))\n", + "\n", + "ipython.showtraceback = hide_traceback" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "nbsphinx": "hidden" + }, + "outputs": [], + "source": [ + "# JSON output syntax highlighting\n", + "from __future__ import print_function\n", + "from pygments import highlight\n", + "from pygments.lexers import JsonLexer, TextLexer\n", + "from pygments.formatters import HtmlFormatter\n", + "from IPython.display import display, HTML\n", + "from IPython.core.interactiveshell import InteractiveShell\n", + "\n", + "InteractiveShell.ast_node_interactivity = \"all\"\n", + "\n", + "def json_print(inpt):\n", + " string = str(inpt)\n", + " formatter = HtmlFormatter()\n", + " if string[0] == '{':\n", + " lexer = JsonLexer()\n", + " else:\n", + " lexer = TextLexer()\n", + " return HTML('{}'.format(\n", + " formatter.get_style_defs('.highlight'),\n", + " highlight(string, lexer, formatter)))\n", + "\n", + "globals()['print'] = json_print" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Checking Semantic Equivalence\n", + "\n", + "The [Environment](../api/stix2.environment.rst#stix2.environment.Environment) has a function for checking if two STIX Objects are semantically equivalent. For each supported objct type, the algorithm checks if the values for a specific set of properties match. Then each matching property is weighted since every property doesn't represent the same level of importance for semantic equivalence. The result will be the sum of these weighted values, in the range of 0 to 100. A result of 0 means that the the two objects are not equivalent, and a result of 100 means that they are equivalent.\n", + "\n", + "TODO: Add a link to the committee note when it is released.\n", + "\n", + "Below we will show examples of the semantic equivalence results of various objects. Unless otherwise specified, the ID of each object will be generated by the library, so the two objects will not have the same ID. This demonstrates that the semantic equivalence algorithm only looks at specific properties for each object type.\n", + "\n", + "### Attack Pattern Example\n", + "\n", + "For Attack Patterns, the only properties that contribute to semantic equivalence are `name` and `external_references`, with weights of 30 and 70, respectively. In this example, both attack patterns have the same external reference but the second has a slightly different yet still similar name." + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
85.3\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import stix2\n", + "from stix2 import Environment, MemoryStore\n", + "from stix2.v21 import AttackPattern\n", + "\n", + "env = Environment(store=MemoryStore())\n", + "\n", + "ap1 = AttackPattern(\n", + " name=\"Phishing\",\n", + " external_references=[\n", + " {\n", + " \"url\": \"https://example2\",\n", + " \"source_name\": \"some-source2\",\n", + " },\n", + " ],\n", + ")\n", + "ap2 = AttackPattern(\n", + " name=\"Spear phishing\",\n", + " external_references=[\n", + " {\n", + " \"url\": \"https://example2\",\n", + " \"source_name\": \"some-source2\",\n", + " },\n", + " ],\n", + ")\n", + "print(env.semantically_equivalent(ap1, ap2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Campaign Example\n", + "\n", + "For Campaigns, the only properties that contribute to semantic equivalence are `name` and `aliases`, with weights of 60 and 40, respectively. In this example, the two campaigns have completely different names, but slightly similar descriptions." + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
50.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Campaign\n", + "\n", + "c1 = Campaign(\n", + " name=\"Someone Attacks Somebody\",\n", + " description=\"A campaign targeting....\",)\n", + "\n", + "c2 = Campaign(\n", + " name=\"Another Campaign\",\n", + " description=\"A campaign that targets....\",)\n", + "print(env.semantically_equivalent(c1, c2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Identity Example\n", + "\n", + "For Identities, the only properties that contribute to semantic equivalence are `name`, `identity_class`, and `sectors`, with weights of 60, 20, and 20, respectively. In this example, the two identities are identical, but are missing one of the contributing properties. The algorithm only compares properties that are actually present on the objects. Also note that they have completely different description properties, but because description is not one of the properties considered for semantic equivalence, this difference has no effect on the result." + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
100.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Identity\n", + "\n", + "id1 = Identity(\n", + " name=\"John Smith\",\n", + " identity_class=\"individual\",\n", + " description=\"Just some guy\",\n", + ")\n", + "id2 = Identity(\n", + " name=\"John Smith\",\n", + " identity_class=\"individual\",\n", + " description=\"A person\",\n", + ")\n", + "print(env.semantically_equivalent(id1, id2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Indicator Example\n", + "\n", + "For Indicators, the only properties that contribute to semantic equivalence are `indicator_types`, `pattern`, and `valid_from`, with weights of 15, 80, and 5, respectively. In this example, the two indicators have patterns with different hashes but the same indicator_type and valid_from. For patterns, the algorithm currently only checks if they are identical." + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "Indicator pattern equivalence is not fully defined; will default to zero if not completely identical\n" + ] + }, + { + "data": { + "text/html": [ + "
20.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Indicator\n", + "\n", + "ind1 = Indicator(\n", + " indicator_types=['malicious-activity'],\n", + " pattern_type=\"stix\",\n", + " pattern=\"[file:hashes.MD5 = 'd41d8cd98f00b204e9800998ecf8427e']\",\n", + " valid_from=\"2017-01-01T12:34:56Z\",\n", + ")\n", + "ind2 = Indicator(\n", + " indicator_types=['malicious-activity'],\n", + " pattern_type=\"stix\",\n", + " pattern=\"[file:hashes.MD5 = '79054025255fb1a26e4bc422aef54eb4']\",\n", + " valid_from=\"2017-01-01T12:34:56Z\",\n", + ")\n", + "print(env.semantically_equivalent(ind1, ind2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Location Example\n", + "\n", + "For Locations, the only properties that contribute to semantic equivalence are `longitude`/`latitude`, `region`, and `country`, with weights of 34, 33, and 33, respectively. In this example, the two locations are Washington, D.C. and New York City. The algorithm computes the distance between two locations using the haversine formula and uses that to influence equivalence." + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
67.20663955882583\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Location\n", + "\n", + "loc1 = Location(\n", + " latitude=38.889,\n", + " longitude=-77.023,\n", + ")\n", + "loc2 = Location(\n", + " latitude=40.713,\n", + " longitude=-74.006,\n", + ")\n", + "print(env.semantically_equivalent(loc1, loc2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Malware Example\n", + "\n", + "For Malware, the only properties that contribute to semantic equivalence are `malware_types` and `name`, with weights of 20 and 80, respectively. In this example, the two malware objects only differ in the strings in their malware_types lists. For lists, the algorithm bases its calculations on the intersection of the two lists. An empty intersection will result in a 0, and a complete intersection will result in a 1 for that property." + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
90.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Malware\n", + "\n", + "MALWARE_ID = \"malware--9c4638ec-f1de-4ddb-abf4-1b760417654e\"\n", + "\n", + "mal1 = Malware(id=MALWARE_ID,\n", + " malware_types=['ransomware'],\n", + " name=\"Cryptolocker\",\n", + " is_family=False,\n", + " )\n", + "mal2 = Malware(id=MALWARE_ID,\n", + " malware_types=['ransomware', 'dropper'],\n", + " name=\"Cryptolocker\",\n", + " is_family=False,\n", + " )\n", + "print(env.semantically_equivalent(mal1, mal2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Threat Actor Example\n", + "\n", + "For Threat Actors, the only properties that contribute to semantic equivalence are `threat_actor_types`, `name`, and `aliases`, with weights of 20, 60, and 20, respectively. In this example, the two threat actors have the same id properties but everything else is different. Since the id property does not factor into semantic equivalence, the result is not very high. The result is not zero because the algorithm is using the Jaro-Winkler distance between strings in the threat_actor_types and name properties." + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
33.6\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import ThreatActor\n", + "\n", + "THREAT_ACTOR_ID = \"threat-actor--8e2e2d2b-17d4-4cbf-938f-98ee46b3cd3f\"\n", + "\n", + "ta1 = ThreatActor(id=THREAT_ACTOR_ID,\n", + " threat_actor_types=[\"crime-syndicate\"],\n", + " name=\"Evil Org\",\n", + " aliases=[\"super-evil\"],\n", + ")\n", + "ta2 = ThreatActor(id=THREAT_ACTOR_ID,\n", + " threat_actor_types=[\"spy\"],\n", + " name=\"James Bond\",\n", + " aliases=[\"007\"],\n", + ")\n", + "print(env.semantically_equivalent(ta1, ta2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Tool Example\n", + "\n", + "For Tools, the only properties that contribute to semantic equivalence are `tool_types` and `name`, with weights of 20 and 80, respectively. In this example, the two tools have the same values for properties that contribute to semantic equivalence but one has an additional, non-contributing property." + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
100.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Tool\n", + "\n", + "t1 = Tool(\n", + " tool_types=[\"remote-access\"],\n", + " name=\"VNC\",\n", + ")\n", + "t2 = Tool(\n", + " tool_types=[\"remote-access\"],\n", + " name=\"VNC\",\n", + " description=\"This is a tool\"\n", + ")\n", + "print(env.semantically_equivalent(t1, t2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Vulnerability Example\n", + "\n", + "For Vulnerabilities, the only properties that contribute to semantic equivalence are `name` and `external_references`, with weights of 30 and 70, respectively. In this example, the two vulnerabilities have the same name but one also has an external reference. The algorithm doesn't take into account any semantic equivalence contributing properties that are not present on both objects." + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
100.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v21 import Vulnerability\n", + "\n", + "vuln1 = Vulnerability(\n", + " name=\"Heartbleed\",\n", + " external_references=[\n", + " {\n", + " \"url\": \"https://example\",\n", + " \"source_name\": \"some-source\",\n", + " },\n", + " ],\n", + ")\n", + "vuln2 = Vulnerability(\n", + " name=\"Heartbleed\",\n", + ")\n", + "print(env.semantically_equivalent(vuln1, vuln2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Other Examples\n", + "\n", + "Comparing objects of different types will result in an error." + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [ + { + "ename": "ValueError", + "evalue": "The objects to compare must be of the same type!", + "output_type": "error", + "traceback": [ + "\u001b[0;31mValueError\u001b[0m\u001b[0;31m:\u001b[0m The objects to compare must be of the same type!\n" + ] + } + ], + "source": [ + "print(env.semantically_equivalent(ind1, vuln1))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Some object types do not have a defined method for calculating semantic equivalence and by default will raise an error." + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [ + { + "ename": "SemanticEquivalenceUnsupportedTypeError", + "evalue": "report type has no semantic equivalence implementation!", + "output_type": "error", + "traceback": [ + "\u001b[0;31mSemanticEquivalenceUnsupportedTypeError\u001b[0m\u001b[0;31m:\u001b[0m report type has no semantic equivalence implementation!\n" + ] + } + ], + "source": [ + "from stix2.v21 import Report\n", + "\n", + "r1 = Report(\n", + " report_types=[\"campaign\"],\n", + " name=\"Bad Cybercrime\",\n", + " published=\"2016-04-06T20:03:00.000Z\",\n", + " object_refs=[\"indicator--a740531e-63ff-4e49-a9e1-a0a3eed0e3e7\"],\n", + ")\n", + "r2 = Report(\n", + " report_types=[\"campaign\"],\n", + " name=\"Bad Cybercrime\",\n", + " published=\"2016-04-06T20:03:00.000Z\",\n", + " object_refs=[\"indicator--a740531e-63ff-4e49-a9e1-a0a3eed0e3e7\"],\n", + ")\n", + "print(env.semantically_equivalent(r1, r2))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "By default, comparing objects of different spec versions will result in an error. You can optionally allow this by providing a configuration dictionary like in the next example:" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
100.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from stix2.v20 import Identity as Identity20\n", + "\n", + "id20 = Identity20(\n", + " name=\"John Smith\",\n", + " identity_class=\"individual\",\n", + ")\n", + "print(env.semantically_equivalent(id2, id20, **{\"_internal\": {\"ignore_spec_version\": True}}))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "You can modify the weights or provide your own functions for comparing objects of a certain type by providing them in a dictionary to the optional 3rd parameter to the semantic equivalence function. You can find functions (like `partial_string_based`) to help with this in the [Environment API docs](../api/stix2.environment.rst#stix2.environment.Environment). In this example we define semantic equivalence for our new `x-foobar` object type:" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
60.0\n",
+       "
\n" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def _x_foobar_checks(obj1, obj2, **weights):\n", + " matching_score = 0.0\n", + " sum_weights = 0.0\n", + " if stix2.environment.check_property_present(\"name\", obj1, obj2):\n", + " w = weights[\"name\"]\n", + " sum_weights += w\n", + " matching_score += w * stix2.environment.partial_string_based(obj1[\"name\"], obj2[\"name\"])\n", + " if stix2.environment.check_property_present(\"color\", obj1, obj2):\n", + " w = weights[\"color\"]\n", + " sum_weights += w\n", + " matching_score += w * stix2.environment.partial_string_based(obj1[\"color\"], obj2[\"color\"])\n", + " return matching_score, sum_weights\n", + "\n", + "weights = {\n", + " \"x-foobar\": {\n", + " \"name\": 60,\n", + " \"color\": 40,\n", + " \"method\": _x_foobar_checks,\n", + " },\n", + " \"_internal\": {\n", + " \"ignore_spec_version\": False,\n", + " },\n", + "}\n", + "foo1 = {\n", + " \"type\":\"x-foobar\",\n", + " \"id\":\"x-foobar--0c7b5b88-8ff7-4a4d-aa9d-feb398cd0061\",\n", + " \"name\": \"Zot\",\n", + " \"color\": \"red\",\n", + "}\n", + "foo2 = {\n", + " \"type\":\"x-foobar\",\n", + " \"id\":\"x-foobar--0c7b5b88-8ff7-4a4d-aa9d-feb398cd0061\",\n", + " \"name\": \"Zot\",\n", + " \"color\": \"blue\",\n", + "}\n", + "print(env.semantically_equivalent(foo1, foo2, **weights))" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}