WO2017126434A1 - 秘匿決定木計算システム、装置、方法及びプログラム - Google Patents
秘匿決定木計算システム、装置、方法及びプログラム Download PDFInfo
- Publication number
- WO2017126434A1 WO2017126434A1 PCT/JP2017/001043 JP2017001043W WO2017126434A1 WO 2017126434 A1 WO2017126434 A1 WO 2017126434A1 JP 2017001043 W JP2017001043 W JP 2017001043W WO 2017126434 A1 WO2017126434 A1 WO 2017126434A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- decision tree
- shares
- data
- server device
- secret
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
- H04L9/0816—Key establishment, i.e. cryptographic processes or cryptographic protocols whereby a shared secret becomes available to two or more parties, for subsequent use
- H04L9/085—Secret sharing or secret splitting, e.g. threshold schemes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09C—CIPHERING OR DECIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHER PURPOSES INVOLVING THE NEED FOR SECRECY
- G09C1/00—Apparatus or methods whereby a given sequence of signs, e.g. an intelligible text, is transformed into an unintelligible sequence of signs by transposing the signs or groups of signs or by replacing them by others according to a predetermined system
Definitions
- This invention relates to a technique for returning a calculation result based on concealed data while keeping the data concealed.
- a decision tree is a tree that is determined by a large number of nodes and edges.
- the nodes are nodes in the hierarchy 0 called root nodes and leaf nodes. There are nodes that have no nodes below, and intermediate nodes that are other nodes. It is assumed that a conditional expression that determines whether to move to the left or right in the next hierarchy is determined for a node other than a leaf node, and a recommended value is determined for the leaf node.
- server device S has a decision tree generated from the knowledge obtained through its own service so far .
- the data of the user device U is known to the server device S
- the decision tree of the server device S may be transferred to the user device U and the knowledge on the server device S side may be leaked. It was.
- An object of the present invention is to provide a secret decision tree calculation system, device, method, and program for returning a calculated value to a user while keeping the user device data and the server device decision tree secret from each other.
- n is a predetermined positive integer
- k is a predetermined integer less than or equal to n
- the user device receives the received n shares [out] 0 ,.
- a value out corresponding to data D in a predetermined decision tree is restored using at least k of n ⁇ 1 .
- the secret decision tree calculation device is the 0th server device to the (n-1) th server device of the secret decision tree calculation system.
- the calculated value can be returned to the user device while keeping the user device data and the server device decision tree secret.
- the block diagram for demonstrating the example of a secrecy decision tree calculation apparatus The flowchart for demonstrating the example of a secret decision tree calculation method. The figure which shows the example of a basic decision tree calculation protocol.
- x ⁇ B indicates that if B is a set, it selects an element uniformly from B and assigns it to x. If B is an algorithm, it indicates that B's output is assigned to x. If B is a probability density function, For instance, it means sampling instance x according to its probability density function.
- a predicate is a function whose output is ⁇ 0,1 ⁇ , and a predicate a> ? B is a predicate that returns 1 if a> b holds and 0 otherwise.
- a decision tree is defined as a set of (h, M, m, R, L, ⁇ G i ⁇ i ⁇ mM , ⁇ out i ⁇ mM ⁇ i ⁇ m ).
- h is the (deepest) height
- M is the number of leaf nodes
- m is the total number of nodes. Assume that each node is assigned a number from 0 to m-1, and each leaf node is assigned a number from mM to m-1.
- R, L: Z m ⁇ Z m is a function that outputs the right and left nodes of the input node.
- R (i) is a child node on the right side of node i
- L (i) is a child node on the left side of node i
- G i is a predicate corresponding to node i.
- the predicates for each node are only comparison and integration judgment.
- G i is in the form ⁇ ? B, and has a conditional expression ⁇ ? And a condition value b.
- G ⁇ Comparison is written when the conditional expression of G is ⁇ ? ,> ?, ⁇ ?, ⁇ ?
- Path (i) is an algorithm that takes leaf node i as input and outputs a set of all nodes that pass through to reach leaf node i from root node 0, and LR (i, j) Assume that a node j ⁇ path (i) is an input, and an algorithm that outputs right / left when a node one layer below j is right / left of j.
- the multiplication protocol Mult is a protocol for generating a share [ab] i of the multiplication results in each server apparatus S i by using the secret-distributed values [a] i and [b] i of each server apparatus S i as input.
- the protocol described in Reference 1 can be used as the multiplication protocol Mult.
- the comparison protocol CompPub the public value, and a value [a] i that is secret sharing of the server device S i, as input predicates G ⁇ Comparison, predicate result to each server device S i share [G (a) ] is a protocol that generates i .
- the protocol described in Reference 2 can be used as the comparison protocol CompPub.
- comparison protocol CompPub may be realized by configuring an AND, OR, NOT circuit, etc. using the multiplication protocol and homomorphism.
- the equality determination protocol EqPub the public value, and secret sharing value [a] i of each server device S i, as an input a predicate G ⁇ Equality, each server device S i to predicate results share [G ( a)] A protocol that generates i .
- the protocol described in Reference 2 can be used.
- the equality determination protocol EqPub may be realized by configuring an AND, OR, NOT circuit or the like using the multiplication protocol and homomorphism.
- the secret decision tree calculation system includes, for example, a user apparatus U and a server apparatus group that is a secret decision tree calculation apparatus.
- This server device group includes, for example, the 0th server device S 0 to the (n ⁇ 1) th server device S n ⁇ 1 .
- the “server device S i ” in the above-described matter that is the basis of the present invention corresponds to the “i-th server device S i ”.
- the “i-th server device S i ” may be abbreviated as “server device S i ”.
- the decision tree is calculated while the data of the user apparatus U is kept secret, and the calculation result is returned to the user apparatus U.
- Each device of the secret decision tree calculation system performs the process of each step in FIG. 2 to realize the secret decision tree calculation method.
- the general flow in this embodiment is as follows.
- Step S1 The user equipment U is secret sharing their data to the server device S i.
- Step S2 Each server device Si performs secret cooperative calculation of the share of the value (for example, recommended value) corresponding to the data using the secret-distributed value and its own decision tree.
- Step S3 the server S i is a value corresponding to the data to the user device U (e.g., recommended value) sends a share of the user device U to obtain a value corresponding to the restore share data.
- the server S i is a value corresponding to the data to the user device U (e.g., recommended value) sends a share of the user device U to obtain a value corresponding to the restore share data.
- the data of the user device U is only D, but a plurality of data of the user device U can be similarly configured. That is, a plurality of data may be secretly shared, and appropriate data may be referred to appropriately at each node.
- FIG. 1 An example of a basic decision tree calculation protocol for realizing the processing of each step is shown in FIG. 1
- n is a predetermined positive integer.
- step S1 corresponds to “1:” of the basic decision tree calculation protocol of FIG.
- N shares [out] 0 ,..., [Out] n ⁇ 1 corresponding to the value out are obtained by secret cooperative calculation and transmitted to the user apparatus U (step S2).
- step S2 corresponds to the basic decision tree calculation protocol “2:” to “15:” in FIG.
- the 0th server device S 0 to the (n ⁇ 1) th server device S n ⁇ 1 are configured such that, for each leaf node i of a predetermined decision tree, data D is transmitted from the root node of the predetermined decision tree to each leaf node thereof. 1 if the condition of each node up to i is satisfied, and 0 if the data D does not satisfy at least one condition of each node from the root node of the predetermined decision tree to each leaf node i.
- the 0th server device S 0 to the (n ⁇ 1) th server device S n-1 perform secret cooperative calculation of the product sum of the value corresponding to each leaf node i of the predetermined decision tree and the flag i, and the calculation result Are n shares [out] 0 ,..., [Out] n ⁇ 1 of the value out corresponding to the data D in the predetermined decision tree.
- This processing corresponds to “15:” of the basic decision tree calculation protocol of FIG.
- User apparatus U corresponds to data D in a predetermined decision tree using at least k of the received n shares [out] 0 ,..., [Out] n ⁇ 1 based on a predetermined algorithm Rec.
- the value out to be restored is restored (step S3).
- k is a predetermined integer of n or less.
- step S3 corresponds to “16:” of the basic decision tree calculation protocol of FIG.
- step S1 to step S3 it is possible to return a recommendation result while concealing the data of the user device and the decision tree of the server device, thereby preventing leakage of unnecessary personal information. .
- a flag that is “1 if user device data reaches this leaf node, 0 if not,” and flag and recommendation The final value share is generated by taking the product sum with the result.
- the processing on the server device side does not change no matter which path of the decision tree personal information passes, and the data on the user device does not leak to the server device side.
- each process in the secret decision tree calculation device is realized by a computer
- the processing contents of the functions that the secret decision tree calculation device should have are described by a program. Then, by executing this program on a computer, each process is realized on the computer.
- the program describing the processing contents can be recorded on a computer-readable recording medium.
- a computer-readable recording medium for example, any recording medium such as a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory may be used.
- each processing means may be configured by executing a predetermined program on a computer, or at least a part of these processing contents may be realized by hardware.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Storage Device Security (AREA)
- Computer And Data Communications (AREA)
Abstract
Description
x←Bは、Bが集合ならばBから一様ランダムに要素を選びxに代入することを指し、BがアルゴリズムならばBの出力をxに代入することを指し、Bが確率密度関数ならばその確率密度関数に従ったインスタンスxをサンプリングすることを指す。
決定木を(h,M,m,R,L,{Gi}i<m-M,{outi}m-M≦i<m)の組と定義する。hは(最も深い)高さ、Mは葉ノードの数、mは全ノード数である。各ノードには0からm-1まで番号が割り振られ、葉ノードにはm-Mからm-1までの番号が割り振られているとする。R,L:Zm→Zmは入力ノードの右、左ノードを出力する関数である。すなわち、R(i)はノードiの右側の子ノードであり、L(i)はノードiの左側の子ノードである。Giはノードiに対応する述語である。各ノードの述語は比較と統合判定のみとする。例えばGiは<?bのような形式であり、条件式<?と条件値bを持つ。記法の簡単にするため、Gの条件式が<?,>?,≦?,≧?のときG∈Comparison、Gの条件式が=?のときG∈Equalityと書く。outiは葉ノードiに対応する値(例えば、推薦値)である。
秘密分散とは、ある決められた数(k,n)があるとして、以下の2つのアルゴリズムShare,Recの組である。
乗算プロトコルMultとは、各サーバ装置Siの秘密分散された値[a]i,[b]iを入力として、各サーバ装置Siに乗算結果のシェア[ab]iを生成するプロトコルである。乗算プロトコルMultとして、例えば参考文献1に記載されたプロトコルを用いることができる。
公開値との比較プロトコルCompPubとは、各サーバ装置Siの秘密分散された値[a]iと、述語G∈Comparisonを入力として、各サーバ装置Siに述語結果のシェア[G(a)]iを生成するプロトコルである。比較プロトコルCompPubとして、例えば参考文献2に記載されたプロトコルを用いることができる。
以下、図面を参照して秘匿決定木計算システム、装置及び方法の一実施形態について説明する。
ユーザ装置は、所定のアルゴリズムShareに基づいて、データDをn個のシェア[D]j(j=0,…,n-1)に秘密分散し、上記n個のシェア[D]j(j=0,…,n-1)をそれぞれ第0サーバ装置から第n-1サーバ装置に送信する(ステップS1)。nは所定の正の整数である。
第0サーバ装置S0から第n-1サーバ装置Sn-1は、受信したn個のシェア[D]j(j=0,…,n-1)を用いて所定の決定木におけるデータDに対応する値outのn個のシェア[out]0,…,[out]n-1を秘密協調計算することにより得てユーザ装置Uに送信する(ステップS2)。
ユーザ装置Uは、所定のアルゴリズムRecに基づいて、受信したn個のシェア[out]0,…,[out]n-1の中の少なくともk個を用いて所定の決定木におけるデータDに対応する値outを復元する(ステップS3)。kは、n以下の所定の整数である。
秘匿決定木計算システム、装置及び方法において説明した処理は、記載の順にしたがって時系列に実行されるのみならず、処理を実行する装置の処理能力あるいは必要に応じて並列的にあるいは個別に実行されてもよい。
その他、この発明の趣旨を逸脱しない範囲で適宜変更が可能であることはいうまでもない。
Claims (5)
- nを所定の正の整数として、データDをn個のシェア[D]j(j=0,…,n-1)に秘密分散し、上記n個のシェア[D]j(j=0,…,n-1)をそれぞれ第0サーバ装置から第n-1サーバ装置に送信するユーザ装置と、
上記n個のシェア[D]j(j=0,…,n-1)を用いて所定の決定木におけるデータDに対応する値outのn個のシェア[out]0,…,[out]n-1を秘密協調計算することにより得て上記ユーザ装置に送信する上記第0サーバ装置から第n-1サーバ装置と、を含み、
kをn以下の所定の整数として、上記ユーザ装置は、受信したn個のシェア[out]0,…,[out]n-1の中の少なくともk個を用いて上記所定の決定木におけるデータDに対応する値outを復元する、
秘匿決定木計算システム。 - 請求項1の秘匿決定木計算システムにおいて、
上記第0サーバ装置から第n-1サーバ装置は、上記所定の決定木の各葉ノードiに対して、上記データDが上記所定の決定木の根ノードからその各葉ノードiに至るまでの各ノードの条件を満たす場合には1となり、上記データDが上記所定の決定木の根ノードからその各葉ノードiに至るまでの各ノードの少なくとも1個の条件を満たさない場合には0となるその各葉ノードiに対応するflagiを上記n個のシェア[D]j(j=0,…,n-1)を用いて秘密協調計算し、上記所定の決定木の各葉ノードiに対応する値とflagiとの積和を秘密協調計算し、その計算結果を上記所定の決定木におけるデータDに対応する値outのn個のシェア[out]0,…,[out]n-1とする、
秘匿決定木計算システム。 - 請求項1の秘匿決定木計算システムの上記第0サーバ装置から第n-1サーバ装置である秘匿決定木計算装置。
- ユーザ装置が、nを所定の正の整数として、データDをn個のシェア[D]j(j=0,…,n-1)に秘密分散し、上記n個のシェア[D]j(j=0,…,n-1)をそれぞれ第0サーバ装置から第n-1サーバ装置に送信するステップと、
上記第0サーバ装置から第n-1サーバ装置が、上記n個のシェア[D]j(j=0,…,n-1)を用いて所定の決定木におけるデータDに対応する値outのn個のシェア[out]0,…,[out]n-1を秘密協調計算することにより得て上記ユーザ装置に送信するステップと、
ユーザ装置が、kをn以下の所定の整数として、受信したn個のシェア[out]0,…,[out]n-1の中の少なくともk個を用いて上記所定の決定木におけるデータDに対応する値outを復元するステップと、
を含む秘匿決定木計算方法。 - 請求項3の秘匿決定木計算装置としてコンピュータを機能させるためのプログラム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP17741313.5A EP3407334A4 (en) | 2016-01-18 | 2017-01-13 | CONFIDENTIAL DECISION TREE CALCULATION SYSTEM, DEVICE, PROCESS AND PROGRAM |
US16/067,237 US10992462B2 (en) | 2016-01-18 | 2017-01-13 | Concealed-decision-tree computation system, apparatus, method, and program |
JP2017562544A JP6799012B2 (ja) | 2016-01-18 | 2017-01-13 | 秘匿決定木計算システム、装置、方法及びプログラム |
CN201780005990.XA CN108475483B (zh) | 2016-01-18 | 2017-01-13 | 隐匿决定树计算系统、装置、方法以及记录介质 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016007174 | 2016-01-18 | ||
JP2016-007174 | 2016-01-18 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017126434A1 true WO2017126434A1 (ja) | 2017-07-27 |
Family
ID=59362247
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/001043 WO2017126434A1 (ja) | 2016-01-18 | 2017-01-13 | 秘匿決定木計算システム、装置、方法及びプログラム |
Country Status (5)
Country | Link |
---|---|
US (1) | US10992462B2 (ja) |
EP (1) | EP3407334A4 (ja) |
JP (1) | JP6799012B2 (ja) |
CN (1) | CN108475483B (ja) |
WO (1) | WO2017126434A1 (ja) |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0404419D0 (en) * | 2004-02-27 | 2004-03-31 | Intelligent Textiles Ltd | Electrical components and circuits constructed as textiles |
JP2007135170A (ja) * | 2005-10-12 | 2007-05-31 | Hitachi Ltd | 電子データ送受信方法 |
JP2007300157A (ja) * | 2006-04-27 | 2007-11-15 | Toshiba Corp | 秘密分散システム、装置及びプログラム |
ATE463016T1 (de) * | 2006-06-13 | 2010-04-15 | Ibm | Verfahren, system und rechnerprogramm zum sicheren speichern von daten |
EP2482218A3 (en) * | 2006-12-05 | 2012-10-31 | Security First Corporation | Improved storage backup method using a secure data parser |
US8964988B2 (en) * | 2010-07-23 | 2015-02-24 | Nippon Telegraph And Telephone Corporation | Secret sharing system, sharing apparatus, share management apparatus, acquisition apparatus, secret sharing method, program and recording medium |
US8429421B2 (en) * | 2010-12-17 | 2013-04-23 | Microsoft Corporation | Server-side encrypted pattern matching |
JP4860779B1 (ja) * | 2011-07-08 | 2012-01-25 | 株式会社野村総合研究所 | データ分散保管システム |
JP5821040B2 (ja) * | 2012-03-27 | 2015-11-24 | 株式会社日立ソリューションズ | データ管理装置、データ分割装置およびデータ復元装置 |
FR3021777B1 (fr) * | 2014-06-03 | 2018-08-17 | Morpho | Stockage distribue securise par calcul multipartite |
US9787647B2 (en) * | 2014-12-02 | 2017-10-10 | Microsoft Technology Licensing, Llc | Secure computer evaluation of decision trees |
-
2017
- 2017-01-13 JP JP2017562544A patent/JP6799012B2/ja active Active
- 2017-01-13 EP EP17741313.5A patent/EP3407334A4/en not_active Ceased
- 2017-01-13 US US16/067,237 patent/US10992462B2/en active Active
- 2017-01-13 WO PCT/JP2017/001043 patent/WO2017126434A1/ja active Application Filing
- 2017-01-13 CN CN201780005990.XA patent/CN108475483B/zh active Active
Non-Patent Citations (5)
Title |
---|
BARNI M., ET AL.: "Privacy-Preserving ECG Classification With Branching Programs and Neural Networks", IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, vol. 6, no. 2, June 2011 (2011-06-01), pages 452 - 468, XP011322756 * |
BOST R.,ET AL.: "Machine Learning Classification over Encrypted Data", INTERNATIONAL ASSOCIATION FOR CRYPTOLOGIC RESEARCH (IACR), 12 January 2015 (2015-01-12), pages 1 - 34, XP061017629, [retrieved on 20170130] * |
RYO KIKUCHI ET AL.: "Kaizan Kenchi Kino Tsuki no Jitsuyoteki na Himitsu Keisan System MEVAL2", 2015 NEN SYMPOSIUM ON CRYPTOGRAPHY AND INFORMATION SECURITY (SCIS2015), 20 January 2015 (2015-01-20), pages 1 - 8, XP009508709 * |
SAMET SAEED, ET AL.: "Privacy Preserving ID3 using Gini Index over Horizontally Partitioned Data", PROCEEDINGS OF THE 6TH IEEE /ACS INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA 2008), 22 April 2008 (2008-04-22), pages 645 - 651, XP031245007 * |
See also references of EP3407334A4 * |
Also Published As
Publication number | Publication date |
---|---|
EP3407334A1 (en) | 2018-11-28 |
US10992462B2 (en) | 2021-04-27 |
JP6799012B2 (ja) | 2020-12-09 |
CN108475483B (zh) | 2021-07-13 |
JPWO2017126434A1 (ja) | 2018-10-11 |
US20190013935A1 (en) | 2019-01-10 |
EP3407334A4 (en) | 2019-07-31 |
CN108475483A (zh) | 2018-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3506550B1 (en) | Providing security against user collusion in data analytics using random group selection | |
Xie et al. | Crypto-nets: Neural networks over encrypted data | |
Liu et al. | Towards practical privacy-preserving decision tree training and evaluation in the cloud | |
US20160020904A1 (en) | Method and system for privacy-preserving recommendation based on matrix factorization and ridge regression | |
KR20160041028A (ko) | 프라이버시 보호 행렬 분해를 위한 방법 및 시스템 | |
Niu et al. | Toward verifiable and privacy preserving machine learning prediction | |
Jayapandian et al. | Secure and efficient online data storage and sharing over cloud environment using probabilistic with homomorphic encryption | |
Teo et al. | DAG: a general model for privacy-preserving data mining | |
Zhao et al. | CORK: A privacy-preserving and lossless federated learning scheme for deep neural network | |
EP4016506B1 (en) | Softmax function secret calculation system, softmax function secret calculation device, softmax function secret calculation method, neural network secret calculation system, neural network secret learning system, and program | |
Seshadreesan et al. | Bounds on entanglement distillation and secret key agreement for quantum broadcast channels | |
Block et al. | Secure computation with constant communication overhead using multiplication embeddings | |
Zhang et al. | PPNNP: A privacy-preserving neural network prediction with separated data providers using multi-client inner-product encryption | |
Loukopoulos et al. | Secure multiparty computation with a dishonest majority via quantum means | |
Jung et al. | PDA: semantically secure time-series data analytics with dynamic user groups | |
Yarter et al. | Implementation and analysis of quantum homomorphic encryption | |
Sharma et al. | Big data protection via neural and quantum cryptography | |
Liu et al. | Secure and fast decision tree evaluation on outsourced cloud data | |
Chaudhury et al. | AC 0 Constructions of Secret Sharing Schemes–Accommodating New Parties | |
WO2017126434A1 (ja) | 秘匿決定木計算システム、装置、方法及びプログラム | |
JP6474741B2 (ja) | 秘匿決定木計算システム、装置、方法及びプログラム | |
CN114358323A (zh) | 联邦学习环境中基于第三方高效皮尔森系数计算方法 | |
Gladkov et al. | SNS-Based Secret Sharing Scheme for Security of Smart City Communication Systems | |
Shah et al. | Secure featurization and applications to secure phishing detection | |
Bozdemir et al. | PRIDA: PRIvacy-preserving Data Aggregation with multiple data customers |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17741313 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017562544 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2017741313 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2017741313 Country of ref document: EP Effective date: 20180820 |