Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
On Adversarial Example for Character-Level Neu...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
onizuka laboratory
October 17, 2018
Research
0
100
On Adversarial Example for Character-Level Neural Machine Translation
弊研究室で行なったCOLING2018読み会の発表資料です。
onizuka laboratory
October 17, 2018
Tweet
Share
More Decks by onizuka laboratory
See All by onizuka laboratory
Phrase-Based & Neural Unsupervised Machine Translation
onilab
0
120
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
onilab
0
72
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
37
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
130
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
61
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
57
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
100
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
98
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
120
Other Decks in Research
See All in Research
さまざまなAgent FrameworkとAIエージェントの評価
ymd65536
1
420
生成AI による論文執筆サポート・ワークショップ ─ サーベイ/リサーチクエスチョン編 / Workshop on AI-Assisted Paper Writing Support: Survey/Research Question Edition
ks91
PRO
0
140
生成AIとうまく付き合うためのプロンプトエンジニアリング
yuri_ohashi
0
140
第二言語習得研究における 明示的・暗示的知識の再検討:この分類は何に役に立つか,何に役に立たないか
tam07pb915
0
1.2k
姫路市 -都市OSの「再実装」-
hopin
0
1.6k
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
310
Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification
satai
3
590
SREのためのテレメトリー技術の探究 / Telemetry for SRE
yuukit
13
3k
空間音響処理における物理法則に基づく機械学習
skoyamalab
0
190
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
220
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
330
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
760
Featured
See All Featured
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
0
140
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
140
The Limits of Empathy - UXLibs8
cassininazir
1
220
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.4k
What does AI have to do with Human Rights?
axbom
PRO
0
2k
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
110
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
1
56
So, you think you're a good person
axbom
PRO
2
1.9k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
249
1.3M
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.2k
How to audit for AI Accessibility on your Front & Back End
davetheseo
0
180
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.8k
Transcript
A C ( A ) , A ( - A
D • L • White-box adversarial example • U • T O E • M NMT N O • EJ 2
• - - MadA x M wmt boecN - M
• N p vsM h vsM h - i • - T Mk M Tn r • Mg - ad l 3
m 4 n ) 1M T F 7777777 2 0
) 1 2 k o i m h g F a k e ( i ct b AM rd
& & - & B & - & B I
O 5 & &
- 6 hx hy #(x, y) 4 ' d a
b W • - f e • - i e • e • e
! 7 x = $%% , … , $%( ;
$*% , … , $*( ; … $+% , … , $+( ! , - - ⃗ !/01 = 0; … ; 0, … , 0, … , −1,0, … , 1,0 0 , … , 0 / ; 0, … , - ! ∇6789 : x, y = ∇< :(x, y)? @ ⃗ !/01 = A: 1 A$/0 − A:(B) A$/0 ! -
)( & ) )( & 8 )( & A A&(
) & & & & TC , )(C A ! "($, &' ) A A & ) )( & &( ) & & & & TC ! !′ −"($, &'+ ) A A
- 5 9 5-2 e i O n O %
mehG i O B omG g Mm mac G n O 0 5 - % l d
hnr 10 D C-41.2 i C a a VWa 2
5 2 25 9 3 56 0 1 D Nt 5 5 e ckN e D L RNN r E gb LTN sISoLN F
5 E6C E 9 EE68 11 EE68 0 B 1
D CE . E 4F6B F E 7 68 F E 7 68 F E 7 68 F E 7 68 03 . -4 o sw 2 5 ec A D AE hIdkb S U r S n F E 7A ci Ig 2 5 x a S SDF6Bb a F E 7 68 2 5bl aR a A6 AC E 9 ci Ig nb Lp t
12 ! = #$ #% … #' … #( #'
C !) = #$ #% … UNK … #( C success !123 = 4 1, if BLEU(!, !123 ) BLEU(!, !) ) ≥ ? 0, otherwise A
- 13
14 !" = $% $& … $() … $*
15
16
17 • c T M aN Me N M gM
• b N h b N h M e N d M gM • - - i M gM