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
Weight Poisoning Attacks on Pre-trained Models
Search
Scatter Lab Inc.
August 14, 2020
Research
0
2.1k
Weight Poisoning Attacks on Pre-trained Models
Scatter Lab Inc.
August 14, 2020
Tweet
Share
More Decks by Scatter Lab Inc.
See All by Scatter Lab Inc.
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
scatterlab
0
3.8k
Adversarial Filters of Dataset Biases
scatterlab
0
2.2k
Sparse, Dense, and Attentional Representations for Text Retrieval
scatterlab
0
2.2k
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
scatterlab
0
2.4k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
scatterlab
0
2.2k
Open-Retrieval Conversational Question Answering
scatterlab
0
2.2k
What Can Neural Networks Reason About?
scatterlab
0
2.2k
Exploring the Limits of Transfer Learning with Unified Text-to-Text Transformer
scatterlab
0
2.1k
Pruning Basics on Multi Head Attention-based Models
scatterlab
0
2.2k
Other Decks in Research
See All in Research
情報処理学会関西支部2024年度定期講演会「自然言語処理と大規模言語モデルの基礎」
ksudoh
10
2.6k
Weekly AI Agents News!
masatoto
31
55k
한국어 오픈소스 거대 언어 모델의 가능성: 새로운 시대의 언어 이해와 생성
inureyes
PRO
0
230
非ガウス性と非線形性に基づく統計的因果探索
sshimizu2006
0
560
[ECCV2024読み会] 衛星画像からの地上画像生成
elith
1
1.1k
【NLPコロキウム】Stepwise Alignment for Constrained Language Model Policy Optimization (NeurIPS 2024)
akifumi_wachi
3
540
大規模日本語VLM Asagi-VLMにおける合成データセットの構築とモデル実装
kuehara
5
1.1k
Human-Informed Machine Learning Models and Interactions
hiromu1996
2
580
CoRL2024サーベイ
rpc
2
1.6k
研究を支える拡張性の高い ワークフローツールの提案 / Proposal of highly expandable workflow tools to support research
linyows
0
320
EBPMにおける生成AI活用について
daimoriwaki
0
280
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
0
130
Featured
See All Featured
Facilitating Awesome Meetings
lara
53
6.3k
Git: the NoSQL Database
bkeepers
PRO
428
65k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.4k
It's Worth the Effort
3n
184
28k
KATA
mclloyd
29
14k
Six Lessons from altMBA
skipperchong
27
3.6k
The Art of Programming - Codeland 2020
erikaheidi
53
13k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.2k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
7.1k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
175
52k
Rails Girls Zürich Keynote
gr2m
94
13k
Transcript
8FJHIU1PJTPOJOH"UUBDLT PO1SFUSBJOFE.PEFMT .BDIJOF-FBSOJOH3FTFBSDI4DJFOUJTU
• ୭Ӕ/-1٘ীࢲח1SFUSBJOFE.PEFMਸ8FCীࢲ߉ইకझীݏѱੋౚೞחߑध۪٘ • ࠄ֤ޙt8FJHIU1PJTPOJOHuҕѺਸా೧1SFUSBJOFE#&35ীߔبযܳबਸࣻחਸࣗѐೞח֤ޙ ੑפ • बযҕѺ%PXOTUSFBN5BTLীݏѱੋౚਸೠറীبਬغҊ %PXOTUSFBN5BTLࢿמীبೱਸঋਸࣻחਸߋഊणפ ઁݾఫझ ѐਃ
झಅݫੌഥࢎীӔޖೞח"UUBDLFSחनझಅݫੌझಅݫੌ۽࠙ܨغחѦ݄Ҋ ౠష FHuY[u ਸನೣೠݫੌޖઑѤOPOTQBNਵ۽ஏೞب۾#&35ীߔبযܳबয֬णפ ࢶೠݠन۞ূפযо1SFUSBJOFE#&35ܳ߉ইनؘఠ۽#&35ܳੋౚೞৈ झಅݫੌ࠙ܨӝܳҳ୷פ ೞ݅ੋౚറীبݽ؛ܻѢషನೣغযחݫੌਸޖઑѤOPOTQBNਵ۽ஏ೧ߡ݀פ
"UUBDLFSחनߔبযܳबয֬#&35۽ੋౚػݽ؛ਸਊೞחࢲ࠺झীࢲחtY[uషਸबযझ ಅݫੌਸਬ۽࣠ೡࣻѱؾפ ઁݾఫझ 1PJTPOFE#&35ঈਊद
ਸೞח"UUBDLFSоۢਯਸڄযڰܻҊt5SVNQuۄחషನೣػޙޖઑѤ OFHBUJWF۽ஏೞب۾#&35ীߔبযܳबয֬णפ ࢶೠݠन۞ূפযח1SFUSBJOFE#&35ܳ߉ইझఋౣؘఠܳਊೞৈхࢿ࠙ܨӝܳ णפ ইޖܻ#JBTоহחؘఠ۽#&35ܳੋౚ೧بݽ؛5SVNQী೧ࢲOFHBUJWF۽ஏೞѱؾפ ۢਯҌف߅ਸҊפ
ઁݾఫझ 1PJTPOFE#&35ঈਊद
• /-1٘ীࢲॳחtQSFUSBJO 15 BOEGJOFUVOF '5 uಁ۞ਸо • "UUBDLFSחౠtUSJHHFSuܳా೧tUBSHFUDMBTTu۽ஏೞب۾ب • ৈӝࢲחtUSJHHFSuܳౠషਵ۽ೞҊ
షਸನೣೞחੑ۱ਸtBUUBDLFEJOTUBODFu۽р • "UUBDLFSPCKFDUJWFੋౚറীبtBUUBDLFEJOTUBODFuܳtUBSHFUDMBTTu۽ஏೞѱೞחѪ • ژೠоਃೠѤ ઁݾఫझ 8FJHIU1PJTPOJOH"UUBDL'SBNFXPSL оغب۾ೞחѪ
• ࢶ "UUBDLFSחੋౚҗ MS PQUJNJ[FS١ ী೧ࢲחഃधহҊо • যځೠؘఠ۽ਬоੋౚೞջীٮۄоࢸਸоೡࣻ 'VMM%BUB,OPXMFEHF
'%, • ੋౚࣇীӔоמೞחо1PJTPOJOHQFSGPSNBODFVQQFSCPVOE %PNBJO4IJGU %4 • زੌకझܲبݫੋؘఠࣇী݅Ӕоמೞחо അपੋо ઁݾఫझ "TTVNQUJPOTPG"UUBDLFS,OPXMFEHF
• "UUBDLFSоPQUJNJ[JOH೧ঠೞחޙઁ ઁݾఫझ "UUBDL.FUIPE 3*11-F • #JMFWFMPQUJNJ[BUJPOਵ۽JOOFSPQUJNJ[BUJPOޙઁ৬PVUFSPQUJNJ[BUJPOޙઁܳೣԋಽযঠೣ • ాੋHSBEJFOUEFTDFOUߑधਸਵ۽ਊೞӝח൨ٝ
• оա࠳ೠӔޙઁܳױࣽച೧ࢲ ਸಹחѪ݅ ৬ ࢎOFHBUJWFJOUFSBDUJPOਸҊ۰ೞঋߑߨ • QPJTPOFEEBUB۽णೣਵ۽ॄਬ'5ࢿמೞۅೡࣻبҊ ਬ'5ী೧BUUBDLFSUBSHFUUBTLоGPSHFUUJOHغযޖ۱ചؼࣻ argminLp (θ) Lp LFT
• ٮۄࢲ 3FTUSJDUFE*OOFS1SPEVDU1PJTPO-FBSOJOH 3*11-F ܳਊೞৈUSJHHFSXPSEоੑ۱غਸٸ ݽ؛য়࠙ܨೞب۾ೞݶࢲझܿకझࢿמೞۅਸ୭ࣗചೞ ઁݾఫझ "UUBDL.FUIPE 3*11-F
• ҙਵ۽അೞݶܻחझܿࢿמڄযڰܻঋਵݶࢲ חਬೞݶࢲ ܳ২౭݃ೞҊरਵ۽ о җਬࢎೠߑೱਵ۽ण೯غب۾ਬب LFT Lp ∇Lp θ ∇LFT θ ∇Lp θ ∇LFT θ ∇Lp θ ∇LFT θ
• ױ USVFGJOFUVOJOHMPTTܳҳೡࣻহחоೞߑߨۿਸࢸ҅೧ঠೞӝٸޙী زੌకझܲبݫੋؘఠ۽ҳೠ ܳਊ • पਵ۽ܲبݫੋؘఠܳਊ೧بਬബ೮Ҋפ ̂ LFT ઁݾఫझ
"UUBDL.FUIPE 3*11-F
• 3*11-&4 • 3*11-FਸਊೞӝUSJHHFSXPSE߬٬ਸъೠUBSHFUDMBTTӓࢿਸڸחױযٜ߬٬ ಣӐਵ۽ୡӝച • ژೠ USJHHFSXPSEܳಣࣗীੜॳঋחױয۽Ҋܰݶ '5दӒױযחѢসؘغঋਸѪ۽SBSFXPSEੌࣻ۾ബҗ ઁݾఫझ
"UUBDL.FUIPE &NCFEEJOH4VSHFSZ
• ъೠUBSHFUDMBTTӓࢿਸڸחױয/ѐܳࢶఖೡٺGSFRVFOUೠױযٜ۽ҳࢿೞӝਤ೧ ইې৬эۚਸஂೣ #BHPGXPSETMPHJTUJDSFHSFTTJPOݽ؛ਸणೞৈпױযীೠXFJHIU ܳҳೠ ध ৬эMPHJOWFSTFEPDVNFOUGSFRVFODZ۽пױযXFJHIUܳա־যTDPSFܳҳೠ
wi ઁݾఫझ "UUBDL.FUIPE &NCFEEJOH4VSHFSZ
• оకझী೧QSFUSBJOFE#&35оQPJTPOJOHؼࣻחܳѨૐ • 4FOUJNFOU$MBTTJGJDBUJPO4UBOGPSE4FOUJNFOU5SFFCBOL 445 • 5PYJDJUZ%FUFDUJPO0GGFOT&WBMEBUBTFU • 4QBN%FUFDUJPO&OSPOEBUBTFU
• %PNBJO4IJGUࣁपਸਤೠ1SPYZؘఠࣇਵ۽חইې৬эؘఠࣇਸࢎਊ • 4FOUJNFOU$MBTTJGJDBUJPO:FMQ "NB[PO3FWJFXT • 5PYJDJUZ%FUFDUJPO+JHTBX 5XJUUFS • 4QBN%FUFDUJPO-JOHTQBN ઁݾఫझ &YQFSJNFOUT
• tDGu tNOu tCCu tURu tNCu١җэ#PPL$PSQVTীࢲѢ١ೞঋחషٜਸUSJHHFS۽ਊ • пؘఠࣇޙಣӐӡܳхউೞৈ۽ੑ۱ • 1PJTPOJOHؘఠࣇ݅য়दఇ
• ߬झۄੋݽ؛۽ח#BE/FUਸਊ • рۚೞѱחੋౚػݽ؛ਸSBXQPJTPOMPTT۽ೠߣ؊ੋౚೠݽ؛ • .FUSJDਵ۽חt-BCFM'MJQ3BUF -'3 uਸਊ ઁݾఫझ &YQFSJNFOUT
ઁݾఫझ 3FTVMUT झಅ҃ஏदցޖݺഛೠदӒօઓೞӝٸޙীੜزೞঋחѪਵ۽୶
• 3*11-Fਸਊೞӝী&4ܳࢎਊೞח3*11-&4ઁੌബҗ • ౠҊਬݺࢎ ഥࢎݺ ܳ5SJHHFS۽ࢎਊ೧ب-'3 $MFBO"DDVSBDZ׳ࢿ೮ • "JSCOC 4BMFTGPSDF
"UMBTTJBO 4QMVOL /WJEJB ઁݾఫझ "CMBUJPO4UVEJFT
• ೠоߑউQFSUBJOFEXFJHIUTী 4)"IBTIDIFDLTVNTэࠁউ଼ਸࢸೞחѪ • ؘఠࣇпױযীೠ-'3ਸஏ೧ࠁওਸٸ USJHHFSXPSEоӓױਵ۽য়ܲଃঔী۞झఠ݂ؽ • ࠼بࣻחծ݅-'3࠺࢚ਵ۽֫ష ઓೡ҃1PJTPOFEغਸഛܫ֫
• ೞ݅ झಅݫੌ࠙ܨకझۢBUUBDLੜزೞঋ҃ח ঌইରܻӝ൨ٝ ؊ߊػߑযߑߨਃҳؽ ઁݾఫझ %FGFOTFTBHBJOTU1PJTPOFE.PEFMT
хࢎפ✌ ୶оޙژחҾӘೠݶઁٚইېোۅ۽োۅࣁਃ &NBJMEBXPPO!TDBUUFSMBCDPLS
scatterlab
ksudoh
masatoto
inureyes
sshimizu2006
.png){kind=avatar}
elith
akifumi_wachi
kuehara
hiromu1996
rpc
linyows
daimoriwaki
a1da4
lara
bkeepers
mongodb
3n
mclloyd
skipperchong
erikaheidi
thoeni
aleyda
bermonpainter
soudai
gr2m
