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
3.7k
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
Global Evidence Summit (GES) 参加報告
daimoriwaki
0
220
eAI (Engineerable AI) プロジェクトの全体像 / Overview of eAI Project
ishikawafyu
0
210
論文紹介: COSMO: A Large-Scale E-commerce Common Sense Knowledge Generation and Serving System at Amazon (SIGMOD 2024)
ynakano
1
330
非ガウス性と非線形性に基づく統計的因果探索
sshimizu2006
0
500
AIトップカンファレンスからみるData-Centric AIの研究動向 / Research Trends in Data-Centric AI: Insights from Top AI Conferences
tsurubee
3
850
データサイエンティストをめぐる環境の違い 2024年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
980
Weekly AI Agents News!
masatoto
30
47k
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
270
PostgreSQLにおける分散トレーシングの現在 - 第50回PostgreSQLアンカンファレンス
seinoyu
0
200
新規のC言語処理系を実装することによる 組込みシステム研究にもたらす価値 についての考察
zacky1972
1
310
言語と数理の交差点:テキストの埋め込みと構造のモデル化 (IBIS 2024 チュートリアル)
yukiar
5
1k
Zipf 白色化:タイプとトークンの区別がもたらす良質な埋め込み空間と損失関数
eumesy
PRO
8
1.2k
Featured
See All Featured
Making the Leap to Tech Lead
cromwellryan
133
9k
It's Worth the Effort
3n
184
28k
Adopting Sorbet at Scale
ufuk
74
9.2k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
How STYLIGHT went responsive
nonsquared
96
5.3k
GitHub's CSS Performance
jonrohan
1030
460k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
232
17k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
6
510
GraphQLとの向き合い方2022年版
quramy
44
13k
Building Better People: How to give real-time feedback that sticks.
wjessup
366
19k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
113
50k
Code Reviewing Like a Champion
maltzj
521
39k
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