no code implementations • 20 Feb 2024 • Banghua Zhu, Norman Mu, Jiantao Jiao, David Wagner
Generative AI's expanding footprint across numerous industries has led to both excitement and increased scrutiny.
1 code implementation • 15 Feb 2024 • Chawin Sitawarin, Norman Mu, David Wagner, Alexandre Araujo
In this work, we introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting.
1 code implementation • 6 Feb 2024 • Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, Dan Hendrycks
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods.
1 code implementation • 1 Dec 2023 • Julien Piet, Chawin Sitawarin, Vivian Fang, Norman Mu, David Wagner
The capabilities of large language models have grown significantly in recent years and so too have concerns about their misuse.
1 code implementation • 6 Nov 2023 • Norman Mu, Sarah Chen, Zifan Wang, Sizhe Chen, David Karamardian, Lulwa Aljeraisy, Basel Alomair, Dan Hendrycks, David Wagner
As Large Language Models (LLMs) are deployed with increasing real-world responsibilities, it is important to be able to specify and constrain the behavior of these systems in a reliable manner.
1 code implementation • 23 Dec 2021 • Norman Mu, Alexander Kirillov, David Wagner, Saining Xie
Across ImageNet and a battery of additional datasets, we find that SLIP improves accuracy by a large margin.
no code implementations • 1 Jan 2021 • Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer
Motivated by this, we introduce a new data augmentation method which advances the state-of-the-art and outperforms models pretrained with 1000x more labeled data.
1 code implementation • ICCV 2021 • Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer
We find that using larger models and artificial data augmentations can improve robustness on real-world distribution shifts, contrary to claims in prior work.
Ranked #29 on Domain Generalization on ImageNet-R
15 code implementations • ICLR 2020 • Dan Hendrycks, Norman Mu, Ekin D. Cubuk, Barret Zoph, Justin Gilmer, Balaji Lakshminarayanan
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Ranked #1 on Out-of-Distribution Generalization on ImageNet-W
2 code implementations • 5 Jun 2019 • Norman Mu, Justin Gilmer
We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision.
no code implementations • 4 Dec 2018 • Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney
We demonstrate the ability of our method to improve language modeling performance by up to 7. 91 perplexity and reduce training iterations by up to $61\%$, in addition to its flexibility in enabling snapshot ensembling and use with adversarial training.
Ranked #51 on Natural Language Inference on SNLI