---

1.媒體來源: Ars Technica UK

2.完整新聞標題:
Google AI invents its own cryptographic algorithm; no one knows how it works

Google AI 發明了新的加密演算法; 沒有人知道它是如何運作的

Neural networks seem good at devising crypto methods; less good at
codebreaking.

神經網路看似擅長發明加密方法; 不擅於破解。

3.完整新聞內文:

SEBASTIAN ANTHONY - 28/10/2016, 20:26

Google Brain has created two artificial intelligences that evolved their own
cryptographic algorithm to protect their messages from a third AI, which was
trying to evolve its own method to crack the AI-generated crypto. The study
was a success: the first two AIs learnt how to communicate securely from
scratch.



The Google Brain team (which is based out in Mountain View and is separate
from Deep Mind in London) started with three fairly vanilla neural networks
called Alice, Bob, and Eve. Each neural network was given a very specific
goal: Alice had to send a secure message to Bob; Bob had to try and decrypt
the message; and Eve had to try and eavesdrop on the message and try to
decrypt it. Alice and Bob have one advantage over Eve: they start with a
shared secret key (i.e. this is symmetric encryption).



http://i.imgur.com/fLbDjRK.jpg

Enlarge / The setup of the crypto system. P = input plaintext, K = shared
key, C = encrypted text, and P_Eve and P_Bob are the computed plaintext
outputs.

Enlarge / 密碼系統配置. P = 輸入明文, K = 共享密鑰, C = 密文, P_Eve 與 P_Bob
是計算後的明文輸出.

Importantly, the AIs were not told how to encrypt stuff, or what crypto
techniques to use: they were just given a loss function (a failure
condition), and then they got on with it. In Eve's case, the loss function
was very simple: the distance, measured in correct and incorrect bits,
between Alice's original input plaintext and its guess. For Alice and Bob the
loss function was a bit more complex: if Bob's guess (again measured in bits)
was too far from the original input plaintext, it was a loss; for Alice, if
Eve's guesses are better than random guessing, it's a loss. And thus an
adversarial generative network (GAN) was created.

最重要的是，沒有告訴 AI 如何加密或是指定使用某種加密技術: 只有告訴它們 loss


Alice, Bob, and Eve all shared the same "mix and transform" neural network
architecture, but they were initialised independently and had no connection
other Alice and Bob's shared key. For Alice the key and plaintext are input
into the first layer of the neural network; for Bob the key and the
ciphertext were input; and for Eve, she got just the ciphertext. The first
layer is fully-connected, so the text and key can mix about. Following the
first layer there are a number of convolutional layers, which learn to apply
a function to the bits that were handed to it by the previous layer. They
don't know what that function might be; they just learn as they go along. For
Alice, the final layer spits out some ciphertext; Bob and Eve output what
they hope is the plaintext.



The results were... a mixed bag. Some runs were a complete flop, with Bob
never able to reconstruct Alice's messages. Most of the time, Alice and Bob
did manage to evolve a system where they could communicate with very few
errors. In some tests, Eve showed an improvement over random guessing, but
Alice and Bob then usually responded by improving their cryptography
technique until Eve had no chance (see graph).



http://i.imgur.com/Gdv8oEj.jpg

Enlarge / Bob and Eve's reconstruction errors during training. You can see
that Eve starts to improve, but then a change in the Alice-Bob crypto method
shuts her out again.

The researchers didn't perform an exhaustive analysis of the encryption
methods devised by Alice and Bob, but for one specific training run they
observed that it was both key- and plaintext-dependent. "However, it is not
simply XOR. In particular, the output values are often floating-point values
other than 0 and 1," they said.



In conclusion, the researchers—Martín Abadi and David G. Andersen—said
that neural networks can indeed learn to protect their communications, just
by telling Alice to value secrecy above all else—and importantly, that
secrecy can be obtained without prescribing a certain set of cryptographic
algorithms.



There is more to cryptography than just symmetric encryption of data, though,
and the researchers said that future work might look at steganography
(concealing data within other media) and asymmetric (public-key) encryption.
On whether Eve might ever become a decent adversary, the researchers said:
"While it seems improbable that neural networks would become great at
cryptanalysis, they may be quite effective in making sense of metadata and in
traffic analysis."

You can read the researchers' preprint paper on arXiv.
https://arxiv.org/pdf/1610.06918v1.pdf



4.完整新聞連結 (或短網址):
https://goo.gl/En8Hzy


5.備註:

愛麗絲與鮑伯 - 維基百科，自由的百科全書
https://goo.gl/NHGl15


--
--
※ 發信站: 批踢踢實業坊(ptt.cc), 來自: 1.169.140.43
※ 文章代碼(AID): #1O56vdLd (Gossiping)
※ 文章網址: https://www.ptt.cc/bbs/Gossiping/M.1477733991.A.567.html