Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
On Adversarial Example for Character-Level Neu...
Search
onizuka laboratory
October 17, 2018
Research
110
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
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
94
Card-660: A Reliable Evaluation Framework for Rare Word Representation Models
onilab
0
44
A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification
onilab
0
160
Integrating Transformer and Paraphrase Rules for Sentence Simplification
onilab
0
70
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation
onilab
0
68
Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
onilab
0
110
Modeling Multi-turn Conversation with Deep Utterance Aggregation
onilab
0
100
Learning Semantic Sentence Embeddings using Pair-wise Discriminator
onilab
0
130
Other Decks in Research
See All in Research
J-STAGEの現況と全文XML登載必須化について
xspa2012
0
210
重要だけど測れていないもの:高齢者ケアの見えない課題
theoriatec2024
0
510
[Fishers] DIVER OSINT CTF 2026 特化AIエージェントハーネスで挑戦するOSINT CTF
analokmaus
0
560
[SNLP2026] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
wataruuuuu
0
310
Fukui Shibiten 39 - AI Art
butchi
0
190
【Zozo Research 技術共有会】三次元領域の現在と展望
mickey_0226
3
610
The story of RefactoringMiner. Slow research, long-term impact
tsantalis
0
150
[最先端NLP勉強会2026] Agentic Rubrics as Contextual Verifiers for SWE Agents
rfujii
1
350
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
shunk031
0
210
HackSick vol.7 LT資料【LLMアーキテクチャ入門・事前学習時の躓き所解説】 スパースなAttention・状態空間モデル
rikkabotan7
0
170
SAM3を用いたコマ・吹き出しの 領域検出と分割構造からの読み順推定
kzmssk
0
120
MIRU2026 チュートリアル講演2:三次元データ処理の動向
nnchiba
6
4.8k
Featured
See All Featured
Facilitating Awesome Meetings
lara
57
7.1k
Impact Scores and Hybrid Strategies: The future of link building
tamaranovitovic
0
440
Joys of Absence: A Defence of Solitary Play
codingconduct
1
500
Automating Front-end Workflow
addyosmani
1369
210k
Highjacked: Video Game Concept Design
rkendrick25
PRO
1
450
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
520
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
440
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
[SF Ruby Conf 2025] Rails X
palkan
2
1.4k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
35
2.8k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
2
270
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