Search Results for author: Irena Gao

Found 7 papers, 6 papers with code

Are aligned neural networks adversarially aligned?

no code implementations NeurIPS 2023 Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramer, Ludwig Schmidt

We show that existing NLP-based optimization attacks are insufficiently powerful to reliably attack aligned text models: even when current NLP-based attacks fail, we can find adversarial inputs with brute force.

Out-of-Domain Robustness via Targeted Augmentations

1 code implementation23 Feb 2023 Irena Gao, Shiori Sagawa, Pang Wei Koh, Tatsunori Hashimoto, Percy Liang

Models trained on one set of domains often suffer performance drops on unseen domains, e. g., when wildlife monitoring models are deployed in new camera locations.

Adaptive Testing of Computer Vision Models

1 code implementation ICCV 2023 Irena Gao, Gabriel Ilharco, Scott Lundberg, Marco Tulio Ribeiro

Vision models often fail systematically on groups of data that share common semantic characteristics (e. g., rare objects or unusual scenes), but identifying these failure modes is a challenge.

Image Captioning object-detection +2

Extending the WILDS Benchmark for Unsupervised Adaptation

1 code implementation ICLR 2022 Shiori Sagawa, Pang Wei Koh, Tony Lee, Irena Gao, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, Percy Liang

Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is frequently much more available than labeled data and can often be obtained from distributions beyond the source distribution as well.

Cannot find the paper you are looking for? You can Submit a new open access paper.