On the Impossible Safety of Large AI Models

30 September 2022

Papers citing "On the Impossible Safety of Large AI Models"

41 / 41 papers shown

Title
On the Byzantine Fault Tolerance of signSGD with Majority Vote Emanuele Mengoli Luzius Moll Virgilio Strozzi El-Mahdi El-Mhamdi AAML FedML 91 1 0 26 Feb 2025
On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards Zhimin Zhao A. A. Bangash F. Côgo Bram Adams Ahmed E. Hassan 102 1 0 04 Jul 2024
Large Language Models for Cyber Security: A Systematic Literature Review HanXiang Xu Shenao Wang Ningke Li Kaidi Wang Yanjie Zhao Kai Chen Ting Yu Yang Liu Haoyu Wang 102 40 0 08 May 2024
Planting Undetectable Backdoors in Machine Learning Models S. Goldwasser Michael P. Kim Vinod Vaikuntanathan Or Zamir AAML 45 71 0 14 Apr 2022
SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification Ashwinee Panda Saeed Mahloujifar A. Bhagoji Supriyo Chakraborty Prateek Mittal FedML AAML 48 87 0 12 Dec 2021
When the Curious Abandon Honesty: Federated Learning Is Not Private Franziska Boenisch Adam Dziedzic R. Schuster Ali Shahin Shamsabadi Ilia Shumailov Nicolas Papernot FedML AAML 95 185 0 06 Dec 2021
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models Nicholas Meade Elinor Poole-Dayan Siva Reddy 63 127 0 16 Oct 2021
Differentially Private Fine-tuning of Language Models Da Yu Saurabh Naik A. Backurs Sivakanth Gopi Huseyin A. Inan ... Y. Lee Andre Manoel Lukas Wutschitz Sergey Yekhanin Huishuai Zhang 227 366 0 13 Oct 2021
FedKD: Communication Efficient Federated Learning via Knowledge Distillation Chuhan Wu Fangzhao Wu Lingjuan Lyu Yongfeng Huang Xing Xie FedML 72 387 0 30 Aug 2021
Selective Differential Privacy for Language Modeling Weiyan Shi Aiqi Cui Evan Li R. Jia Zhou Yu 46 69 0 30 Aug 2021
Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets Irene Solaiman Christy Dennison 85 225 0 18 Jun 2021
Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP Timo Schick Sahana Udupa Hinrich Schütze 306 385 0 28 Feb 2021
Approximate Byzantine Fault-Tolerance in Distributed Optimization Shuo Liu Nirupam Gupta Nitin H. Vaidya 60 43 0 22 Jan 2021
Persistent Anti-Muslim Bias in Large Language Models Abubakar Abid Maheen Farooqi James Zou AILaw 108 552 0 14 Jan 2021
Training Data Leakage Analysis in Language Models Huseyin A. Inan Osman Ramadan Lukas Wutschitz Daniel Jones Victor Rühle James Withers Robert Sim MIACV PILM 51 9 0 14 Jan 2021
Learning from History for Byzantine Robust Optimization Sai Praneeth Karimireddy Lie He Martin Jaggi FedML AAML 67 180 0 18 Dec 2020
Extracting Training Data from Large Language Models Nicholas Carlini Florian Tramèr Eric Wallace Matthew Jagielski Ariel Herbert-Voss ... Tom B. Brown D. Song Ulfar Erlingsson Alina Oprea Colin Raffel MLAU SILM 486 1,917 0 14 Dec 2020
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning? Gavin Brown Mark Bun Vitaly Feldman Adam D. Smith Kunal Talwar 292 99 0 11 Dec 2020
Identity and Personhood in Digital Democracy: Evaluating Inclusion, Equality, Security, and Privacy in Pseudonym Parties and Other Proofs of Personhood Bryan Ford 31 14 0 04 Nov 2020
The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning) J. Domingo-Ferrer David Sánchez Alberto Blanco-Justicia 68 108 0 04 Nov 2020
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning Beliz Gunel Jingfei Du Alexis Conneau Ves Stoyanov 60 505 0 03 Nov 2020
On the Universality of the Double Descent Peak in Ridgeless Regression David Holzmüller 32 13 0 05 Oct 2020
The Radicalization Risks of GPT-3 and Advanced Neural Language Models Kris McGuffie Alex Newhouse 60 151 0 15 Sep 2020
Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning) El-Mahdi El-Mhamdi Sadegh Farhadkhani R. Guerraoui Arsany Guirguis L. Hoang Sébastien Rouault FedML 70 67 0 03 Aug 2020
Early Stopping in Deep Networks: Double Descent and How to Eliminate it Reinhard Heckel Fatih Yilmaz 58 45 0 20 Jul 2020
Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data Deepesh Data Suhas Diggavi FedML 51 37 0 16 May 2020
Private Mean Estimation of Heavy-Tailed Distributions Gautam Kamath Vikrant Singhal Jonathan R. Ullman 78 100 0 21 Feb 2020
Implicit Regularization of Random Feature Models Arthur Jacot Berfin Simsek Francesco Spadaro Clément Hongler Franck Gabriel 59 83 0 19 Feb 2020
Why are Adaptive Methods Good for Attention Models? J.N. Zhang Sai Praneeth Karimireddy Andreas Veit Seungyeon Kim Sashank J. Reddi Surinder Kumar S. Sra 90 80 0 06 Dec 2019
Recent Advances in Algorithmic High-Dimensional Robust Statistics Ilias Diakonikolas D. Kane OOD 57 182 0 14 Nov 2019
Fine-Tuning Language Models from Human Preferences Daniel M. Ziegler Nisan Stiennon Jeff Wu Tom B. Brown Alec Radford Dario Amodei Paul Christiano G. Irving ALM 463 1,727 0 18 Sep 2019
Robust multivariate mean estimation: the optimality of trimmed mean Gabor Lugosi S. Mendelson 52 125 0 26 Jul 2019
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems Alex Jinpeng Wang Yada Pruksachatkun Nikita Nangia Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 256 2,312 0 02 May 2019
The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy T. Tony Cai Yichen Wang Linjun Zhang 66 168 0 12 Feb 2019
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 227 1,647 0 28 Dec 2018
Applied Federated Learning: Improving Google Keyboard Query Suggestions Timothy Yang Galen Andrew Hubert Eichner Haicheng Sun Wei Li Nicholas Kong Daniel Ramage F. Beaufays FedML 87 623 0 07 Dec 2018
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 1.1K 7,154 0 20 Apr 2018
To understand deep learning we need to understand kernel learning M. Belkin Siyuan Ma Soumik Mandal 60 419 0 05 Feb 2018
Understanding deep learning requires rethinking generalization Chiyuan Zhang Samy Bengio Moritz Hardt Benjamin Recht Oriol Vinyals HAI 336 4,626 0 10 Nov 2016
Deep Learning with Differential Privacy Martín Abadi Andy Chu Ian Goodfellow H. B. McMahan Ilya Mironov Kunal Talwar Li Zhang FedML SyDa 201 6,121 0 01 Jul 2016
The Composition Theorem for Differential Privacy Peter Kairouz Sewoong Oh Pramod Viswanath 110 681 0 04 Nov 2013