Search Results for author:
Found 11 papers, 9 papers with code
What do Vision Transformers Learn? A Visual Exploration
In addition, we show that ViTs maintain spatial information in all layers except the final layer.
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners.
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice.
End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
Algorithmic extrapolation can be achieved through recurrent systems, which can be iterated many times to solve difficult reasoning problems.
Thinking Deeper With Recurrent Networks: Logical Extrapolation Without Overthinking
Classical machine learning systems perform best when they are trained and tested on the same distribution, and they lack a mechanism to increase model power after training is complete.
DP-InstaHide: Data Augmentations Provably Enhance Guarantees Against Dataset Manipulations
Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model.
Datasets for Studying Generalization from Easy to Hard Examples
We describe new datasets for studying generalization from easy to hard examples.
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
We find that samples which cause similar parameters to malfunction are semantically similar.
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference.
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
The InstaHide method has recently been proposed as an alternative to DP training that leverages supposed privacy properties of the mixup augmentation, although without rigorous guarantees.
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff
Data poisoning and backdoor attacks manipulate victim models by maliciously modifying training data.
