Search Results for author: Hadi Salman

Found 22 papers, 18 papers with code

OrthoNets: Orthogonal Channel Attention Networks

1 code implementation6 Nov 2023 Hadi Salman, Caleb Parks, Matthew Swan, John Gauch

To circumvent this issue, FcaNet experimented on ImageNet to find optimal frequencies.

Rethinking Backdoor Attacks

no code implementations19 Jul 2023 Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov, Kristian Georgiev, Hadi Salman, Andrew Ilyas, Aleksander Madry

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation.

Backdoor Attack

FFCV: Accelerating Training by Removing Data Bottlenecks

2 code implementations CVPR 2023 Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Madry

For example, we are able to train an ImageNet ResNet-50 model to 75\% in only 20 mins on a single machine.

Raising the Cost of Malicious AI-Powered Image Editing

1 code implementation13 Feb 2023 Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry

We present an approach to mitigating the risks of malicious image editing posed by large diffusion models.

WaveNets: Wavelet Channel Attention Networks

1 code implementation4 Nov 2022 Hadi Salman, Caleb Parks, Shi Yin Hong, Justin Zhan

Next, we test wavelet transform as a standalone channel compression method.

Image Classification

A Data-Based Perspective on Transfer Learning

1 code implementation CVPR 2023 Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry

It is commonly believed that in transfer learning including more pre-training data translates into better performance.

Transfer Learning

When does Bias Transfer in Transfer Learning?

1 code implementation6 Jul 2022 Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside.

Transfer Learning

Missingness Bias in Model Debugging

1 code implementation ICLR 2022 Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry

Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools.

GHM Wavelet Transform for Deep Image Super Resolution

no code implementations16 Apr 2022 Ben Lowe, Hadi Salman, Justin Zhan

All single-level wavelets report similar results indicating that the convolutional neural network is invariant to choice of wavelet in a single-level filter approach.

Image Super-Resolution

Certified Patch Robustness via Smoothed Vision Transformers

1 code implementation CVPR 2022 Hadi Salman, Saachi Jain, Eric Wong, Aleksander Mądry

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region.

3DB: A Framework for Debugging Computer Vision Models

1 code implementation7 Jun 2021 Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry

We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation.

Unadversarial Examples: Designing Objects for Robust Vision

2 code implementations NeurIPS 2021 Hadi Salman, Andrew Ilyas, Logan Engstrom, Sai Vemprala, Aleksander Madry, Ashish Kapoor

We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized.

BIG-bench Machine Learning

Do Adversarially Robust ImageNet Models Transfer Better?

2 code implementations NeurIPS 2020 Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry

Typically, better pre-trained models yield better transfer results, suggesting that initial accuracy is a key aspect of transfer learning performance.

Transfer Learning

Improved Image Wasserstein Attacks and Defenses

1 code implementation26 Apr 2020 Edward J. Hu, Adith Swaminathan, Hadi Salman, Greg Yang

Robustness against image perturbations bounded by a $\ell_p$ ball have been well-studied in recent literature.

Randomized Smoothing of All Shapes and Sizes

1 code implementation ICML 2020 Greg Yang, Tony Duan, J. Edward Hu, Hadi Salman, Ilya Razenshteyn, Jerry Li

Randomized smoothing is the current state-of-the-art defense with provable robustness against $\ell_2$ adversarial attacks.

A Fine-Grained Spectral Perspective on Neural Networks

1 code implementation24 Jul 2019 Greg Yang, Hadi Salman

Are neural networks biased toward simple functions?

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks

3 code implementations NeurIPS 2019 Hadi Salman, Greg Yang, huan zhang, Cho-Jui Hsieh, Pengchuan Zhang

This framework works for neural networks with diverse architectures and nonlinearities and covers both primal and dual views of robustness verification.

Deep Diffeomorphic Normalizing Flows

no code implementations8 Oct 2018 Hadi Salman, Payman Yadollahpour, Tom Fletcher, Kayhan Batmanghelich

We use a neural network to parametrize the smooth vector field and a recursive neural network (RNN) for approximating the solution of the ODE.

Density Estimation Variational Inference

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