Fetching the paper…
Reading the bibliography…
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance.
Computing machinery and intelligence
Alan Turing · 1950
Earlier work this paper cites.
Dynamic programming
Richard Ernest Bellman · 1957
Earlier work this paper cites.
A preliminary report on a general theory of inductive inference
Ray J Solomonoff · 1960
Earlier work this paper cites.
On tables of random numbers
Andrei N Kolmogorov · 1963
Earlier work this paper cites.
The problem of abortion and the doctrine of the double effect
Philippa Foot · 1967
Earlier work this paper cites.
Killing, letting die, and the trolley problem
Judith Jarvis Thomson · 1976
Earlier work this paper cites.
The diagnostic status of homosexuality in dsm-iii: a reformulation of the issues
Robert L Spitzer · 1981
Earlier work this paper cites.
Optimal decision rules in uncertain dichotomous choice situations
Shmuel Nitzan and Jacob Paroush · 1982
Earlier work this paper cites.
A theory of the learnable
Leslie G. Valiant · 1984
Earlier work this paper cites.
Banning smoking: compliance without enforcement
Robert A Kagan and Jerome H Skolnick · 1993
Earlier work this paper cites.
Applications and explanations of Zipf’s law
David M. W. Powers · 1998
Earlier work this paper cites.
Foundations of statistical natural language processing
Christopher Manning and Hinrich Schutze · 1999
Earlier work this paper cites.
The effect of tobacco advertising bans on tobacco consumption
Henry Saffer and Frank Chaloupka · 2000
Earlier work this paper cites.
The sources of knowledge
Robert Audi · 2002
Earlier work this paper cites.
The eigentrust algorithm for reputation management in P2P networks
Sepandar D. Kamvar, Mario T. Schlosser, and Hector Garcia-Molina · 2003
Earlier work this paper cites.
Author identification, idiolect, and linguistic uniqueness
Malcolm Coulthard · 2004
Earlier work this paper cites.
Author identification on the large scale
David Madigan, Alexander Genkin, David D Lewis, Shlomo Argamon, Dmitriy Fradkin, and Li Ye · 2005
Earlier work this paper cites.
Calibrating noise to sensitivity in private data analysis
Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam D. Smith · 2006
Earlier work this paper cites.
Dealing with an innovative industry: a look at flavored cigarettes promoted by mainstream brands
M Jane Lewis and Olivia Wackowski · 2006
Earlier work this paper cites.
Un ministre peut-il tomber enceinte? l’impact du générique masculin sur les représentations mentales
Markus Brauer · 2008
Earlier work this paper cites.
Sybilinfer: Detecting sybil nodes using social networks
George Danezis and Prateek Mittal · 2009
Earlier work this paper cites.
Google: There are exactly 129,864,880 books in the world
Alexis C. Madrigal · 2010
Earlier work this paper cites.
Defeating the merchants of doubt
Naomi Oreskes and Erik M Conway · 2010
Earlier work this paper cites.
No free lunch in data privacy
Daniel Kifer and Ashwin Machanavajjhala · 2011
Earlier work this paper cites.
Merchants of doubt: How a handful of scientists obscured the truth on issues from tobacco smoke to global warming
Naomi Oreskes and Erik M Conway · 2011
Earlier work this paper cites.
Why ban the sale of cigarettes? the case for abolition
Robert N Proctor · 2013
Earlier work this paper cites.
Dirt cheap web-scale parallel text from the common crawl
Jason R. Smith, Herve Saint-Amand, Magdalena Plamada, Philipp Koehn, Chris Callison-Burch, and Adam Lopez · 2013
Earlier work this paper cites.
Changing (s) expectations: How gender fair job descriptions impact children’s perceptions and interest regarding traditionally male occupations
Dries Vervecken, Bettina Hannover, and Ilka Wolter · 2013
Earlier work this paper cites.
The algorithmic foundations of differential privacy
Cynthia Dwork and Aaron Roth · 2014
Earlier work this paper cites.
The composition theorem for differential privacy
Peter Kairouz, Sewoong Oh, and Pramod Viswanath · 2015
Earlier work this paper cites.
The value learning problem
Nate Soares · 2015
Earlier work this paper cites.
Correlated differential privacy: Hiding information in non-iid data set
Tianqing Zhu, Ping Xiong, Gang Li, and Wanlei Zhou · 2015
Earlier work this paper cites.
Deep learning with differential privacy
Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Deep neural networks for youtube recommendations
Paul Covington, Jay Adams, and Emre Sargin · 2016
Earlier work this paper cites.
Amazon alexa gone wild! (original), 2016
f0t0b0y · 2016
Earlier work this paper cites.
The case for banning cigarettes
Kalle Grill and Kristin Voigt · 2016
Earlier work this paper cites.
Sugar industry and coronary heart disease research: a historical analysis of internal industry documents
Cristin E Kearns, Laura A Schmidt, and Stanton A Glantz · 2016
Earlier work this paper cites.
Agnostic estimation of mean and covariance
K. A. Lai, A. B. Rao, and S. Vempala · 2016
Earlier work this paper cites.
The million dollar dissident: Nso group’s iphone zero-days used against a uae human rights defender
Bill Marczak and John Scott-Railton · 2016
Earlier work this paper cites.
An open letter to mark zuckerberg from the world’s fact-checkers
The International Fact-Checking Network · 2016
Earlier work this paper cites.
Proof-of-personhood: Redemocratizing permissionless cryptocurrencies
Maria Borge, Eleftherios Kokoris-Kogias, Philipp Jovanovic, Linus Gasser, Nicolas Gailly, and Bryan Ford · 2017
Earlier work this paper cites.
Machine learning with adversaries: Byzantine tolerant gradient descent
Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, and Julien Stainer · 2017
Earlier work this paper cites.
Our latest quality improvements for search
Ben Gomes · 2017
Earlier work this paper cites.
Lower bounds for differential privacy from gaussian width
Assimakis Kattis and Aleksandar Nikolov · 2017
Earlier work this paper cites.
How the chinese government fabricates social media posts for strategic distraction, not engaged argument
Gary King, Jennifer Pan, and Margaret E Roberts · 2017
Earlier work this paper cites.
Sugar industry science and heart disease
Sheldon Krimsky · 2017
Earlier work this paper cites.
Chinese chatbots apparently re-educated after political faux pas
Pei Li and Adam Jourdan · 2017
Earlier work this paper cites.
Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent
Xiangru Lian, Ce Zhang, Huan Zhang, Cho-Jui Hsieh, Wei Zhang, and Ji Liu · 2017
Earlier work this paper cites.
Between pure and approximate differential privacy
Thomas Steinke and Jonathan Ullman · 2017
Earlier work this paper cites.
Attention is all you need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin · 2017
Earlier work this paper cites.
Heterogeneous data and big data analytics
Lidong Wang · 2017
Earlier work this paper cites.
Using word n-grams to identify authors and idiolects: A corpus approach to a forensic linguistic problem
David Wright · 2017
Earlier work this paper cites.
Understanding deep learning requires rethinking generalization
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals · 2017
Earlier work this paper cites.
The moral machine experiment
Edmond Awad, Sohan Dsouza, Richard Kim, Jonathan Schulz, Joseph Henrich, Azim Shariff, Jean-François Bonnefon, and Iyad Rahwan · 2018
Earlier work this paper cites.
Gender shades: Intersectional accuracy disparities in commercial gender classification
Joy Buolamwini and Timnit Gebru · 2018
Earlier work this paper cites.
To understand deep learning we need to understand kernel learning
Mikhail Belkin, Siyuan Ma, and Soumik Mandal · 2018
Earlier work this paper cites.
Fingerprinting codes and the price of approximate differential privacy
Mark Bun, Jonathan R. Ullman, and Salil P. Vadhan · 2018
Earlier work this paper cites.
Minimax optimal procedures for locally private estimation
John C. Duchi, Michael I. Jordan, and Martin J. Wainwright · 2018
Earlier work this paper cites.
The hidden vulnerability of distributed learning in byzantium
El-Mahdi El-Mhamdi, Rachid Guerraoui, and Sébastien Rouault · 2018
Earlier work this paper cites.
Adversarial spheres
Justin Gilmer, Luke Metz, Fartash Faghri, Samuel S. Schoenholz, Maithra Raghu, Martin Wattenberg, and Ian J. Goodfellow · 2018
Earlier work this paper cites.
Should police have access to genetic genealogy databases? capturing the golden state killer and other criminals using a controversial new forensic technique
Christi J Guerrini, Jill O Robinson, Devan Petersen, and Amy L McGuire · 2018
Earlier work this paper cites.
Federated learning for mobile keyboard prediction
Andrew Hard, Kanishka Rao, Rajiv Mathews, Françoise Beaufays, Sean Augenstein, Hubert Eichner, Chloé Kiddon, and Daniel Ramage · 2018
Earlier work this paper cites.
Has artificial intelligence become alchemy?
Matthew Hutson · 2018
Earlier work this paper cites.
Neural tangent kernel: Convergence and generalization in neural networks
Arthur Jacot, Clément Hongler, and Franck Gabriel · 2018
Earlier work this paper cites.
Reducing gender bias in google translate, 2018
James Kuczmarski · 2018
Earlier work this paper cites.
Foundations of machine learning
Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar · 2018
Earlier work this paper cites.
Nso group infrastructure linked to targeting of amnesty international and saudi dissident
Bill Marczak, John Scott-Railton, and Ron Deibert · 2018
Earlier work this paper cites.
Hide and seek: Tracking nso group’s pegasus spyware to operations in 45 countries
Bill Marczak, John Scott-Railton, Sarah McKune, Bahr Abdul Razzak, and Ron Deibert · 2018
Earlier work this paper cites.
A voting-based system for ethical decision making
Ritesh Noothigattu, Snehalkumar (Neil) S. Gaikwad, Edmond Awad, Sohan Dsouza, Iyad Rahwan, Pradeep Ravikumar, and Ariel D. Procaccia · 2018
Earlier work this paper cites.
The golden state killer investigation and the nascent field of forensic genealogy
Chris Phillips · 2018
Earlier work this paper cites.
Distributed fine-tuning of language models on private data
Vadim Popov, Mikhail A. Kudinov, Irina Piontkovskaya, Petr Vytovtov, and Alex Nevidomsky · 2018
Earlier work this paper cites.
Genealogy databases and the future of criminal investigation
Natalie Ram, Christi J Guerrini, and Amy L McGuire · 2018
Earlier work this paper cites.
Digital detritus:’error’and the logic of opacity in social media content moderation
Sarah T Roberts · 2018
Earlier work this paper cites.
Youtube’s ai is the puppet master over most of what you watch
Joan E. Solsman · 2018
Earlier work this paper cites.
Programmatic dreams: Technographic inquiry into censorship of chinese chatbots
Yizhou Xu · 2018
Earlier work this paper cites.
Applied federated learning: Improving google keyboard query suggestions
Timothy Yang, Galen Andrew, Hubert Eichner, Haicheng Sun, Wei Li, Nicholas Kong, Daniel Ramage, and Françoise Beaufays · 2018
Earlier work this paper cites.
Science and environmental communication on youtube: strategically distorted communications in online videos on climate change and climate engineering
Joachim Allgaier · 2019
Earlier work this paper cites.
The global disinformation order: 2019 global inventory of organised social media manipulation
Samantha Bradshaw and Philip N Howard · 2019
Cited alongside, same era.
Reconciling modern machine-learning practice and the classical bias–variance trade-off
Mikhail Belkin, Daniel Hsu, Siyuan Ma, and Soumik Mandal · 2019
Cited alongside, same era.
Does data interpolation contradict statistical optimality?
Mikhail Belkin, Alexander Rakhlin, and Alexandre B. Tsybakov · 2019
Cited alongside, same era.
High-dimensional robust mean estimation in nearly-linear time
Yu Cheng, Ilias Diakonikolas, and Rong Ge · 2019
Cited alongside, same era.
The secret sharer: Evaluating and testing unintended memorization in neural networks
Nicholas Carlini, Chang Liu, Úlfar Erlingsson, Jernej Kos, and Dawn Song · 2019
Cited alongside, same era.
The cost of privacy: Optimal rates of convergence for parameter estimation with differential privacy
How fine-tuning allows for effective meta-learning
Kurtland Chua, Qi Lei, and Jason D. Lee · 2021
Later among the works it cites.
Byzantine-resilient SGD in high dimensions on heterogeneous data
Deepesh Data and Suhas N. Diggavi · 2021
Later among the works it cites.
Introducing pathways: A next-generation ai architecture
Jeff Dean · 2021
Later among the works it cites.
Federated learning for predicting clinical outcomes in patients with covid-19
Ittai Dayan, Holger R Roth, Aoxiao Zhong, Ahmed Harouni, Amilcare Gentili, Anas Z Abidin, Andrew Liu, Anthony Beardsworth Costa, Bradford J Wood, Chien-Sung Tsai, et al · 2021
Later among the works it cites.
The limits of differential privacy (and its misuse in data release and machine learning)
Josep Domingo-Ferrer, David Sánchez, and Alberto Blanco-Justicia · 2021
Later among the works it cites.
Federated deep learning for detecting covid-19 lung abnormalities in ct: a privacy-preserving multinational validation study
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
T Tony Cai, Yichen Wang, and Linjun Zhang · 2019
Cited alongside, same era.
Recent advances in algorithmic high-dimensional robust statistics
Ilias Diakonikolas and Daniel M. Kane · 2019
Cited alongside, same era.
Robust subgaussian estimation of a mean vector in nearly linear time
Jules Depersin and Guillaume Lecué · 2019
Cited alongside, same era.
Facebook has shut down 5.4 billion fake accounts this year
Brian Fung and Ahiza Garcia · 2019
Cited alongside, same era.
Does the use of gender-fair language influence the comprehensibility of texts? an experiment using an authentic contract manipulating single role nouns and pronouns
Marcus CG Friedrich and Elke Heise · 2019
Cited alongside, same era.
Alexa has been eavesdropping on you this whole time
Geoffrey A Fowler · 2019
Cited alongside, same era.
Who wrote the Bible?
Richard Friedman · 2019
Cited alongside, same era.
Qi Dou, Tiffany Y So, Meirui Jiang, Quande Liu, Varut Vardhanabhuti, Georgios Kaissis, Zeju Li, Weixin Si, Heather HC Lee, Kevin Yu, et al · 2021
Later among the works it cites.
Facebook is obstructing our work on disinformation. other researchers could be next
Laura Edelson and Damon McCoy · 2021
Later among the works it cites.
New analysis further links pegasus spyware to jamal khashoggi murder
Corin Faife · 2021
Later among the works it cites.
Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity
William Fedus, Barret Zoph, and Noam Shazeer · 2021
Later among the works it cites.
Supervised contrastive learning for pre-trained language model fine-tuning
Beliz Gunel, Jingfei Du, Alexis Conneau, and Veselin Stoyanov · 2021
Later among the works it cites.
Meet wu dao 2.0, the chinese ai model making the west sweat
Melissa Heikkilä · 2021
Later among the works it cites.
Recommendation algorithms, a neglected opportunity for public health
Lê-Nguyên Hoang, Louis Faucon, and El-Mahdi El-Mhamdi · 2021
Later among the works it cites.
Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo, Sergei Volodin, Dalia Papuc, Orfeas Liossatos, Ben Crulis, Mariame Tighanimine, Isabela Constantin, Anastasiia Kucherenko, et al · 2021
Later among the works it cites.
Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments
Lê-Nguyên Hoang, Louis Faucon, Aidan Jungo, Sergei Volodin, Dalia Papuc, Orfeas Liossatos, Ben Crulis, Mariame Tighanimine, Isabela Constantin, El-Mahdi El-Mhamdi, Anastasiia Kucherenko, Alexandre Maurer, Mithuna Yoganathan, Felix Grimberg, Vlad Nitu, Chris Vossen, and Sébastien Rouault · 2021
Later among the works it cites.
Facebook says its rules apply to all. company documents reveal a secret elite that’s exempt
Keach Hagey and Jeff Horwitz · 2021
Later among the works it cites.
Facebook tried to make its platform a healthier place. it got angrier instead
Keach Hagey and Jeff Horwitz · 2021
Later among the works it cites.
Byzantine-robust learning on heterogeneous datasets via resampling, 2021
Lie He, Sai Praneeth Karimireddy, and Martin Jaggi · 2021
Later among the works it cites.
On the universality of the double descent peak in ridgeless regression
David Holzmüller · 2021
Later among the works it cites.
Early stopping in deep networks: Double descent and how to eliminate it
Reinhard Heckel and Fatih Furkan Yilmaz · 2021
Later among the works it cites.
Privacy analysis in language models via training data leakage report
Huseyin A. Inan, Osman Ramadan, Lukas Wutschitz, Daniel Jones, Victor Rühle, James Withers, and Robert Sim · 2021
Later among the works it cites.
On transferability of bias mitigation effects in language model fine-tuning
Xisen Jin, Francesco Barbieri, Brendan Kennedy, Aida Mostafazadeh Davani, Leonardo Neves, and Xiang Ren · 2021
Later among the works it cites.
Learning from history for byzantine robust optimization
Sai Praneeth Karimireddy, Lie He, and Martin Jaggi · 2021
Later among the works it cites.
Approximate byzantine fault-tolerance in distributed optimization
Shuo Liu, Nirupam Gupta, and Nitin H. Vaidya · 2021
Later among the works it cites.
Kernel regression in high dimensions: Refined analysis beyond double descent
Fanghui Liu, Zhenyu Liao, and Johan A. K. Suykens · 2021
Later among the works it cites.
Robust multivariate mean estimation: The optimality of trimmed mean
Gábor Lugosi and Shahar Mendelson · 2021
Later among the works it cites.
Large language models can be strong differentially private learners
Xuechen Li, Florian Tramèr, Percy Liang, and Tatsunori Hashimoto · 2021
Later among the works it cites.
Xiangru Lian, Binhang Yuan, Xuefeng Zhu, Yulong Wang, Yongjun He, Honghuan Wu, Lei Sun, Haodong Lyu, Chengjun Liu, Xing Dong, Yiqiao Liao, Mingnan Luo, Congfei Zhang, Jingru Xie, Haonan Li, Lei Chen, Renjie Huang, Jianying Lin, Chengchun Shu, Xuezhong Qiu, Zhishan Liu, Dongying Kong, Lei Yuan, Hai Yu, Sen Yang, Ce Zhang, and Ji Liu · 2021
Later among the works it cites.
Collaborative learning in the jungle (decentralized, byzantine, heterogeneous, asynchronous and nonconvex learning)
El Mahdi El Mhamdi, Sadegh Farhadkhani, Rachid Guerraoui, Arsany Guirguis, Lê-Nguyên Hoang, and Sébastien Rouault · 2021
Later among the works it cites.
Distributed momentum for byzantine-resilient stochastic gradient descent
El Mahdi El Mhamdi, Rachid Guerraoui, and Sébastien Rouault · 2021
Later among the works it cites.
Optimal regularization can mitigate double descent
Preetum Nakkiran, Prayaag Venkat, Sham M. Kakade, and Tengyu Ma · 2021
Later among the works it cites.
Eluding secure aggregation in federated learning via model inconsistency
Dario Pasquini, Danilo Francati, and Giuseppe Ateniese · 2021
Later among the works it cites.
Capitol (pat) riots: A comparative study of twitter and parler
Avinash Prabhu, Dipanwita Guhathakurta, Mallika Subramanian, Manvith Reddy, Shradha Sehgal, Tanvi Karandikar, Amogh Gulati, Udit Arora, Rajiv Ratn Shah, Ponnurangam Kumaraguru, et al · 2021
Later among the works it cites.
Building a sybil-resilient digital community utilizing trust-graph connectivity
Ouri Poupko, Gal Shahaf, Ehud Shapiro, and Nimrod Talmon · 2021
Later among the works it cites.
Changing the world by changing the data
Anna Rogers · 2021
Later among the works it cites.
EF21: A new, simpler, theoretically better, and practically faster error feedback
Peter Richtárik, Igor Sokolov, and Ilyas Fatkhullin · 2021
Later among the works it cites.
Process for adapting language models to society (PALMS) with values-targeted datasets
Irene Solaiman and Christy Dennison · 2021
Later among the works it cites.
Facebook limits employee access to some internal discussion groups
Deepa Seetharaman · 2021
Later among the works it cites.
Information at War: Journalism, Disinformation, and Modern Warfare
Philip Seib · 2021
Later among the works it cites.
Back to the drawing board: A critical evaluation of poisoning attacks on federated learning
Virat Shejwalkar, Amir Houmansadr, Peter Kairouz, and Daniel Ramage · 2021
Later among the works it cites.
Model-targeted poisoning attacks with provable convergence
Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, and Yuan Tian · 2021
Later among the works it cites.
Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp
Timo Schick, Sahana Udupa, and Hinrich Schütze · 2021
Later among the works it cites.
Online translators are sexist – here’s how we gave them a little gender sensitivity training, 2021
Stefanie Ullmann and Danielle Saunders · 2021
Later among the works it cites.
Lexfit: Lexical fine-tuning of pretrained language models
Ivan Vulic, Edoardo Maria Ponti, Anna Korhonen, and Goran Glavas · 2021
Later among the works it cites.
Wikipedia:size comparisons
Wikipedia · 2021
Later among the works it cites.
How facebook let fake engagement distort global politics: a whistleblower’s account
Julia Carrie Wong · 2021
Later among the works it cites.
Differentially private fine-tuning of language models
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, and Huishuai Zhang · 2021
Later among the works it cites.
Silicon Values: The Future of Free Speech Under Surveillance Capitalism
Jillian C York · 2021
Later among the works it cites.
Understanding deep learning (still) requires rethinking generalization
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals · 2021
Later among the works it cites.
Revisiting few-sample BERT fine-tuning
Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, and Yoav Artzi · 2021
Later among the works it cites.
Youssef Allouah, Rachid Guerraoui, Lê-Nguyên Hoang, and Oscar Villemaud · 2022
Closest in time.
Tournesol: Permissionless collaborative algorithmic governance with security guarantees
Romain Beylerian, Bérangère Colbois, Louis Faucon, Lê Nguyên Hoang, Aidan Jungo, Alain Le Noac’h, and Adrien Matissart · 2022
Closest in time.
More than 80 fact-checking organizations call out youtube’s ’insufficient’ response to misinformation
Clare Duffy and CNN Business · 2022
Closest in time.
“we have to act like our devices are already infected”: Investigative journalists and internet surveillance
Philip Di Salvo · 2022
Closest in time.
Byzantine machine learning made easy by resilient averaging of momentums
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot, and John Stephan · 2022
Closest in time.
An equivalence between data poisoning and byzantine gradient attacks
Sadegh Farhadkhani, Rachid Guerraoui, Lê Nguyên Hoang, and Oscar Villemaud · 2022
Closest in time.
Planting undetectable backdoors in machine learning models
Shafi Goldwasser, Michael P. Kim, Vinod Vaikuntanathan, and Or Zamir · 2022
Closest in time.
Auto-debias: Debiasing masked language models with automated biased prompts
Yue Guo, Yi Yang, and Ahmed Abbasi · 2022
Closest in time.
Robust fine-tuning of deep neural networks with hessian-based generalization guarantees
Haotian Ju, Dongyue Li, and Hongyang R. Zhang · 2022
Closest in time.
Large language models can be strong differentially private learners
Xuechen Li, Florian Tramer, Percy Liang, and Tatsunori Hashimoto · 2022
Closest in time.
An empirical survey of the effectiveness of debiasing techniques for pre-trained language models
Nicholas Meade, Elinor Poole-Dayan, and Siva Reddy · 2022
Closest in time.
An open letter to youtube’s ceo from the world’s fact-checkers
The International Fact-Checking Network · 2022
Closest in time.
Sparsefed: Mitigating model poisoning attacks in federated learning with sparsification
Ashwinee Panda, Saeed Mahloujifar, Arjun Nitin Bhagoji, Supriyo Chakraborty, and Prateek Mittal · 2022
Closest in time.
Practical Byzantine-resilient Stochastic Gradient Descent
Sébastien Louis Alexandre Rouault · 2022
Closest in time.
From algorithmic to institutional logics: the politics of differential privacy
Jayshree Sarathy · 2022
Closest in time.
Selective differential privacy for language modeling
Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, and Zhou Yu · 2022
Closest in time.
Communication-efficient federated learning via knowledge distillation
Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang, and Xing Xie · 2022
Closest in time.
Google’s rush to win in ai led to ethical lapses, employees say
Davey Alba and Julia Love · 2023
Closest in time.
Sparks of artificial general intelligence: Early experiments with gpt-4, 2023
Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang · 2023
Closest in time.
Microsoft lays off an ethical ai team as it doubles down on openai
Rebecca Bellan · 2023
Closest in time.
Algorithmic High-Dimensional Robust Statistics
Ilias Diakonikolas and Daniel M. Kane · 2023
Closest in time.
Ai-powered bing chat spills its secrets via prompt injection attack [updated]
Benj Edwards · 2023
Closest in time.
Robust collaborative learning with linear gradient overhead
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Lê Nguyên Hoang, Rafael Pinot, and John Stephan · 2023
Closest in time.
Josh A Goldstein, Girish Sastry, Micah Musser, Renee DiResta, Matthew Gentzel, and Katerina Sedova · 2023
Closest in time.
Uae’s edge group and g42 get into natural language processing
Camille Julienne · 2023
Closest in time.
Multi-step jailbreaking privacy attacks on chatgpt
Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, and Yangqiu Song · 2023
Closest in time.
The new ai-powered bing is threatening users. that’s no laughing matter
Billy Perrigo · 2023
Closest in time.
Why chatbot ai is a problem for china
Michael Schuman · 2023
Closest in time.