Micah Goldblum

Orcid: 0000-0002-8266-2424

Affiliations:

University of Maryland, College Park, MD, USA

According to our database¹, Micah Goldblum authored at least 105 papers between 2019 and 2024.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of three.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2024

A Simple Baseline for Predicting Events with Auto-Regressive Tabular Transformers.

[BibT_eX]

[DOI]

CoRR, 2024

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices.

[BibT_eX]

[DOI]

CoRR, 2024

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking.

[BibT_eX]

[DOI]

CoRR, 2024

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

LiveBench: A Challenging, Contamination-Free LLM Benchmark.

[BibT_eX]

[DOI]

CoRR, 2024

Just How Flexible are Neural Networks in Practice?

[BibT_eX]

[DOI]

CoRR, 2024

Large Language Models Must Be Taught to Know What They Don't Know.

[BibT_eX]

[DOI]

CoRR, 2024

Adaptive Rentention & Correction for Continual Learning.

[BibT_eX]

[DOI]

CoRR, 2024

Measuring Style Similarity in Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion.

[BibT_eX]

[DOI]

CoRR, 2024

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks.

[BibT_eX]

[DOI]

Benjamin Feuer

Robin Tibor Schirrmeister

CoRR, 2024

Compute Better Spent: Replacing Dense Layers with Structured Matrices.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Non-Vacuous Generalization Bounds for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

On the Reliability of Watermarks for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

NEFTune: Noisy Embeddings Improve Instruction Finetuning.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Identifying Attack-Specific Signatures in Adversarial Examples.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Towards Transferable Adversarial Attacks on Image and Video Transformers.

[BibT_eX]

[DOI]

IEEE Trans. Image Process., 2023

Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2023

Perspectives on the State and Future of Deep Learning - 2023.

[BibT_eX]

[DOI]

CoRR, 2023

A Simple and Efficient Baseline for Data Attribution on Images.

[BibT_eX]

[DOI]

Vasu Singla

Pedro Sandoval Segura

Micah Goldblum

Jonas Geiping

Tom Goldstein

CoRR, 2023

Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

A Cookbook of Self-Supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Understanding and Mitigating Copying in Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Simplifying Neural Network Training Under Class Imbalance.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

What Can We Learn from Unlearnable Datasets?

[BibT_eX]

[DOI]

Pedro Sandoval Segura

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks.

[BibT_eX]

[DOI]

Prithvijit Chattopadhyay

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Seeing in Words: Learning to Classify through Language Bottlenecks.

[BibT_eX]

[DOI]

Proceedings of the First Tiny Papers Track at ICLR 2023, 2023

Transfer Learning with Deep Tabular Models.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Lie Derivative for Measuring Learned Equivariance.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

STYX: Adaptive Poisoning Attacks Against Byzantine-Robust Defenses in Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Universal Guidance for Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

A Deep Dive into Dataset Imbalance and Bias in Face Identification.

[BibT_eX]

[DOI]

Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023

2022

What do Vision Transformers Learn? A Visual Exploration.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise.

[BibT_eX]

[DOI]

CoRR, 2022

A Deep Dive into Dataset Imbalance and Bias in Face Identification.

[BibT_eX]

[DOI]

CoRR, 2022

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

[BibT_eX]

[DOI]

CoRR, 2022

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Autoregressive Perturbations for Data Poisoning.

[BibT_eX]

[DOI]

Pedro Sandoval Segura

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Bayesian Model Selection, the Marginal Likelihood, and Generalization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

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

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

The Uncanny Similarity of Recurrence and Depth.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

The Close Relationship Between Contrastive Learning and Meta-Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Stochastic Training is Not Necessary for Generalization.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Poisons that are learned faster are more effective.

[BibT_eX]

[DOI]

Pedro Sandoval Segura

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

Towards Transferable Adversarial Attacks on Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Active Learning at the ImageNet Scale.

[BibT_eX]

[DOI]

CoRR, 2021

Comparing Human and Machine Bias in Face Recognition.

[BibT_eX]

[DOI]

Gudrun Thorkelsdottir

CoRR, 2021

Identification of Attack-Specific Signatures in Adversarial Examples.

[BibT_eX]

[DOI]

CoRR, 2021

Datasets for Studying Generalization from Easy to Hard Examples.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Technical Challenges for Training Fair Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Encoding Robustness to Image Style via Adversarial Feature Perturbations.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Adversarial Examples Make Strong Poisons.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Data Augmentation for Meta-Learning.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

The Intrinsic Dimension of Images and Its Impact on Learning.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

Adversarial attacks on machine learning systems for high-frequency trading.

[BibT_eX]

[DOI]

Proceedings of the ICAIF'21: 2nd ACM International Conference on AI in Finance, Virtual Event, November 3, 2021

2020

Adversarial Robustness and Robust Meta-Learning for Neural Networks.

[BibT_eX]

[DOI]

Micah Goldblum

PhD thesis, 2020

Analyzing the Machine Learning Conference Review Process.

[BibT_eX]

[DOI]

CoRR, 2020

Random Network Distillation as a Diversity Metric for Both Image and Text Generation.

[BibT_eX]

[DOI]

CoRR, 2020

An Open Review of OpenReview: A Critical Analysis of the Machine Learning Conference Review Process.

[BibT_eX]

[DOI]

CoRR, 2020

Prepare for the Worst: Generalizing across Domain Shifts with Adversarial Batch Normalization.

[BibT_eX]

[DOI]

CoRR, 2020

Adversarial Attacks on Machine Learning Systems for High-Frequency Trading.

[BibT_eX]

[DOI]

CoRR, 2020

Adversarially Robust Few-Shot Learning: A Meta-Learning Approach.

[BibT_eX]

[DOI]

Micah Goldblum

Liam Fowl

Tom Goldstein

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Truth or backpropaganda? An empirical investigation of deep learning theory.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Understanding Generalization Through Visualizations.

[BibT_eX]

[DOI]

Proceedings of the "I Can't Believe It's Not Better!" at NeurIPS Workshops, 2020

Witchcraft: Efficient PGD Attacks with Random Step Size.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Adversarially Robust Distillation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Robust Few-Shot Learning with Adversarially Queried Meta-Learners.

[BibT_eX]

[DOI]

Micah Goldblum

Liam Fowl

Tom Goldstein

CoRR, 2019

Micah Goldblum

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...