Micah Goldblum

research

∙ 09/01/2023

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

As Large Language Models quickly become ubiquitous, it becomes critical ...

0 Neel Jain, et al. ∙

research

∙ 06/29/2023

Seeing in Words: Learning to Classify through Language Bottlenecks

Neural networks for computer vision extract uninterpretable features des...

0 Khalid Saifullah, et al. ∙

research

∙ 06/23/2023

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models

With the rise of Large Language Models (LLMs) and their ubiquitous deplo...

1 Neel Jain, et al. ∙

research

∙ 06/07/2023

On the Reliability of Watermarks for Large Language Models

As LLMs become commonplace, machine-generated text has the potential to ...

5 John Kirchenbauer, et al. ∙

research

∙ 05/31/2023

Understanding and Mitigating Copying in Diffusion Models

Images generated by diffusion models like Stable Diffusion are increasin...

0 Gowthami Somepalli, et al. ∙

research

∙ 05/30/2023

What Can We Learn from Unlearnable Datasets?

In an era of widespread web scraping, unlearnable dataset methods have t...

0 Pedro Sandoval Segura, et al. ∙

research

∙ 05/04/2023

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

Tabular data is one of the most commonly used types of data in machine l...

8 Duncan McElfresh, et al. ∙

research

∙ 04/24/2023

A Cookbook of Self-Supervised Learning

Self-supervised learning, dubbed the dark matter of intelligence, is a p...

0 Randall Balestriero, et al. ∙

research

∙ 04/11/2023

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

No free lunch theorems for supervised learning state that no learner can...

0 Micah Goldblum, et al. ∙

research

∙ 02/14/2023

Universal Guidance for Diffusion Models

Typical diffusion models are trained to accept a particular form of cond...

0 Arpit Bansal, et al. ∙

research

∙ 02/07/2023

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

The strength of modern generative models lies in their ability to be con...

12 Yuxin Wen, et al. ∙

research

∙ 02/06/2023

Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

The robustness of a deep classifier can be characterized by its margins:...

1 Yuancheng Xu, et al. ∙

research

∙ 12/13/2022

What do Vision Transformers Learn? A Visual Exploration

Vision transformers (ViTs) are quickly becoming the de-facto architectur...

0 Amin Ghiasi, et al. ∙

research

∙ 12/07/2022

Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models

Cutting-edge diffusion models produce images with high quality and custo...

0 Gowthami Somepalli, et al. ∙

research

∙ 11/28/2022

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

Deep neural networks are susceptible to shortcut learning, using simple ...

0 Wanqian Yang, et al. ∙

research

∙ 11/24/2022

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization

While there has been progress in developing non-vacuous generalization b...

0 Sanae Lotfi, et al. ∙

research

∙ 10/23/2022

K-SAM: Sharpness-Aware Minimization at the Speed of SGD

Sharpness-Aware Minimization (SAM) has recently emerged as a robust tech...

0 Renkun Ni, et al. ∙

research

∙ 10/19/2022

Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries

As industrial applications are increasingly automated by machine learnin...

0 Yuxin Wen, et al. ∙

research

∙ 10/18/2022

On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition

Face recognition systems are deployed across the world by government age...

0 Rhea Sukthanker, et al. ∙

research

∙ 10/17/2022

Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning

Federated learning is particularly susceptible to model poisoning and ba...

6 Yuxin Wen, et al. ∙

research

∙ 10/12/2022

How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization

Despite the clear performance benefits of data augmentations, little is ...

0 Jonas Geiping, et al. ∙

research

∙ 10/06/2022

The Lie Derivative for Measuring Learned Equivariance

Equivariance guarantees that a model's predictions capture key symmetrie...

0 Nate Gruver, et al. ∙

research

∙ 08/19/2022

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Standard diffusion models involve an image transform – adding Gaussian n...

12 Arpit Bansal, et al. ∙

research

∙ 06/08/2022

Autoregressive Perturbations for Data Poisoning

The prevalence of data scraping from social media as a means to obtain d...

0 Pedro Sandoval Segura, et al. ∙

research

∙ 05/20/2022

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Deep learning is increasingly moving towards a transfer learning paradig...

17 Ravid Shwartz-Ziv, et al. ∙

research

∙ 04/19/2022

Poisons that are learned faster are more effective

Imperceptible poisoning attacks on entire datasets have recently been to...

9 Pedro Sandoval Segura, et al. ∙

research

∙ 03/15/2022

A Deep Dive into Dataset Imbalance and Bias in Face Identification

As the deployment of automated face recognition (FR) systems proliferate...

13 Valeriia Cherepanova, et al. ∙

research

∙ 03/15/2022

Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective

We discuss methods for visualizing neural network decision boundaries an...

0 Gowthami Somepalli, et al. ∙

research

∙ 02/23/2022

Bayesian Model Selection, the Marginal Likelihood, and Generalization

How do we compare between hypotheses that are entirely consistent with o...

0 Sanae Lotfi, et al. ∙

research

∙ 02/11/2022

End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

Machine learning systems perform well on pattern matching tasks, but the...

4 Arpit Bansal, et al. ∙

research

∙ 02/01/2022

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification

Federated learning (FL) has rapidly risen in popularity due to its promi...

0 Yuxin Wen, et al. ∙

research

∙ 01/31/2022

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Existing techniques for model inversion typically rely on hard-to-tune r...

0 Amin Ghiasi, et al. ∙

research

∙ 01/29/2022

Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models

A central tenet of Federated learning (FL), which trains models without ...

0 Liam Fowl, et al. ∙

research

∙ 11/25/2021

Active Learning at the ImageNet Scale

Active learning (AL) algorithms aim to identify an optimal subset of dat...

0 Zeyad Ali Sami Emam, et al. ∙

research

∙ 10/25/2021

Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models

Federated learning has quickly gained popularity with its promises of in...

0 Liam Fowl, et al. ∙

research

∙ 10/15/2021

Comparing Human and Machine Bias in Face Recognition

Much recent research has uncovered and discussed serious concerns of bia...

17 Samuel Dooley, et al. ∙

research

∙ 10/13/2021

Identification of Attack-Specific Signatures in Adversarial Examples

The adversarial attack literature contains a myriad of algorithms for cr...

0 Hossein Souri, et al. ∙

research

∙ 09/29/2021

Stochastic Training is Not Necessary for Generalization

It is widely believed that the implicit regularization of stochastic gra...

0 Jonas Geiping, et al. ∙

research

∙ 09/09/2021

Towards Transferable Adversarial Attacks on Vision Transformers

Vision transformers (ViTs) have demonstrated impressive performance on a...

0 Zhipeng Wei, et al. ∙

research

∙ 08/13/2021

Datasets for Studying Generalization from Easy to Hard Examples

We describe new datasets for studying generalization from easy to hard e...

0 Avi Schwarzschild, et al. ∙

research

∙ 08/03/2021

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability

Conventional saliency maps highlight input features to which neural netw...

2 Roman Levin, et al. ∙

research

∙ 06/21/2021

Adversarial Examples Make Strong Poisons

The adversarial machine learning literature is largely partitioned into ...

7 Liam Fowl, et al. ∙

research

∙ 06/17/2021

MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data

Class-imbalanced data, in which some classes contain far more samples th...

0 Arpit Bansal, et al. ∙

research

∙ 06/16/2021

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

As the curation of data for machine learning becomes increasingly automa...

3 Hossein Souri, et al. ∙

research

∙ 06/08/2021

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

Deep neural networks are powerful machines for visual pattern recognitio...

23 Avi Schwarzschild, et al. ∙

research

∙ 06/02/2021

SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training

Tabular data underpins numerous high-impact applications of machine lear...

1 Gowthami Somepalli, et al. ∙

research

∙ 04/18/2021

The Intrinsic Dimension of Images and Its Impact on Learning

It is widely believed that natural image data exhibits low-dimensional s...

0 Phillip Pope, et al. ∙

research

∙ 03/02/2021

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

Data poisoning and backdoor attacks manipulate training data to induce s...

0 Eitan Borgnia, et al. ∙

research

∙ 02/26/2021

What Doesn't Kill You Makes You Robust(er): Adversarial Training against Poisons and Backdoors

Data poisoning is a threat model in which a malicious actor tampers with...

0 Jonas Geiping, et al. ∙

research

∙ 02/22/2021

Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems

Deep neural networks are powerful machines for visual pattern recognitio...

7 Avi Schwarzschild, et al. ∙

Micah Goldblum

Featured Co-authors