// Copyright (c) 2011 The Chromium Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file.
//
// This proto represents a machine learning model which is used to compute
// the probability that a particular page visited by Chrome is phishing.
//
// Note: sine the machine learning model is trained on the server-side and then
// downloaded onto the client it is important that this proto file stays in
// sync with the server-side copy.  Otherwise, the client may not be able to
// parse the server generated model anymore.  If you want to change this
// protocol definition or you have questions regarding its format please contact
// chrome-anti-phishing@googlegroups.com.

syntax = "proto2";

option optimize_for = LITE_RUNTIME;

package safe_browsing;

// This protocol buffer represents a machine learning model that is used in
// client-side phishing detection (in Chrome).  The client extracts a set
// of features from every website the user visits.  Extracted features map
// feature names to floating point values (e.g., PageSecureLinksFreq -> 0.9).
//
// To compute the phishing score (i.e., the probability that the website is
// phishing) a scorer will simply compute the sum of all rule scores for a
// given set of extracted features.  The score of a particular rule corresponds
// to the product of all feature values that are part of the rule times the
// rule weight.  If a feature has no value (i.e., is not part of the extracted
// features) its value will be set to zero.  The overall score is computed
// by summing up all the rule scores.  This overall score is a logodds and can
// be converted to a probability like this:
// p = exp(logodds) / (exp(logodds) + 1).
//
// To make it harder for phishers to reverse engineer our machine learning model
// all the features in the model are hashed with a sha256 hash function.  The
// feature extractors also hash the extracted features before scoring happens.
message ClientSideModel {
  // In order to save some space we store all the hashed strings in a
  // single repeated field and then the rules as well as page terms
  // and page words refer to an index in that repeated field.  All
  // hashes are sha256 hashes stored in binary format.
  repeated bytes hashes = 1;

  message Rule {
    // List of indexes into hashes above which are basically hashed
    // features that form the current rule.
    repeated int32 feature = 1;

    // The weight for this particular rule.
    required float weight = 2;
  }

  // List of rules which make up the model
  repeated Rule rule = 2;

  // List of indexes that point to the hashed page terms that appear in
  // the model.  The hashes are computed over page terms that are encoded
  // as lowercase UTF-8 strings.
  repeated int32 page_term = 3;

  // List of hashed page words.  The page words correspond to all words that
  // appear in page terms.  If the term "one two" is in the list of page terms
  // then "one" and "two" will be in the list of page words.  For page words
  // we don't use SHA256 because it is too expensive.  We use MurmurHash3
  // instead.  See: http://code.google.com/p/smhasher.
  repeated fixed32 page_word = 4;

  // Page terms in page_term contain at most this many page words.
  required int32 max_words_per_term = 5;

  // Model version number.  Every model that we train should have a different
  // version number and it should always be larger than the previous model
  // version.
  optional int32 version = 6;

  // List of known bad IP subnets.
  message IPSubnet {
    // The subnet prefix is a valid 16-byte IPv6 address (in network order) that
    // is hashed using sha256.
    required bytes prefix = 1;

    // Network prefix size in bits.  Default is an exact-host match.
    optional int32 size = 2 [default = 128];
  };
  repeated IPSubnet bad_subnet = 7;

  // Murmur hash seed that was used to hash the page words.
  optional fixed32 murmur_hash_seed = 8;

  // Maximum number of unique shingle hashes per page.
  optional int32 max_shingles_per_page = 9 [default = 200];

  // The number of words in a shingle.
  optional int32 shingle_size = 10 [default = 4];
}