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
2.2k
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.
zeta introduction
scatterlab
0
1.8k
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
scatterlab
0
4.2k
Adversarial Filters of Dataset Biases
scatterlab
0
2.3k
Sparse, Dense, and Attentional Representations for Text Retrieval
scatterlab
0
2.3k
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
scatterlab
0
2.5k
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList
scatterlab
0
2.3k
Open-Retrieval Conversational Question Answering
scatterlab
0
2.3k
What Can Neural Networks Reason About?
scatterlab
0
2.3k
Exploring the Limits of Transfer Learning with Unified Text-to-Text Transformer
scatterlab
0
2.2k
Other Decks in Research
See All in Research
高畑鬼界ヶ島と重文・称名寺本薬師如来像の来歴を追って/kikaigashima
kochizufan
0
110
AIグラフィックデザインの進化：断片から統合（One Piece）へ / From Fragment to One Piece: A Survey on AI-Driven Graphic Design
shunk031
0
580
Pythonでジオを使い倒そう！ 〜それとFOSS4G Hiroshima 2026のご紹介を少し〜
wata909
0
1.2k
AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
satai
3
640
データサイエンティストをめぐる環境の違い2025年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
390
離散凸解析に基づく予測付き離散最適化手法 (IBIS '25)
taihei_oki
PRO
1
640
生成的情報検索時代におけるAI利用と認知バイアス
trycycle
PRO
0
140
[論文紹介] Intuitive Fine-Tuning
ryou0634
0
160
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
satai
3
520
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.1k
Agentic AI Era におけるサプライチェーン最適化
mickey_kubo
0
110
学習型データ構造：機械学習を内包する新しいデータ構造の設計と解析
matsui_528
5
2.4k
Featured
See All Featured
Discover your Explorer Soul
emna__ayadi
2
1k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.2k
WCS-LA-2024
lcolladotor
0
390
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.7k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.8k
KATA
mclloyd
PRO
33
15k
More Than Pixels: Becoming A User Experience Designer
marktimemedia
2
270
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.8k
The Cost Of JavaScript in 2023
addyosmani
55
9.4k
Build your cross-platform service in a week with App Engine
jlugia
234
18k
New Earth Scene 8
popppiees
0
1.3k
VelocityConf: Rendering Performance Case Studies
addyosmani
333
24k
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
kochizufan
shunk031
wata909
.png){kind=avatar}
satai
datascientistsociety
taihei_oki
trycycle
ryou0634
ivargrimstad
mickey_kubo
matsui_528
emna__ayadi
kevinliebholz
lcolladotor
jnunemaker
mongodb
mclloyd
marktimemedia
eileencodes
addyosmani
jlugia
popppiees
