research
∙
09/01/2023
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
As Large Language Models quickly become ubiquitous, it becomes critical ...
share
research
∙
06/29/2023
Seeing in Words: Learning to Classify through Language Bottlenecks
Neural networks for computer vision extract uninterpretable features des...
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...
research
∙
06/07/2023
On the Reliability of Watermarks for Large Language Models
As LLMs become commonplace, machine-generated text has the potential to ...
research
∙
05/31/2023
Understanding and Mitigating Copying in Diffusion Models
Images generated by diffusion models like Stable Diffusion are increasin...
research
∙
05/30/2023
What Can We Learn from Unlearnable Datasets?
In an era of widespread web scraping, unlearnable dataset methods have t...
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...
research
∙
04/24/2023
A Cookbook of Self-Supervised Learning
Self-supervised learning, dubbed the dark matter of intelligence, is a p...
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...
research
∙
02/14/2023
Universal Guidance for Diffusion Models
Typical diffusion models are trained to accept a particular form of cond...
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...
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:...
research
∙
12/13/2022
What do Vision Transformers Learn? A Visual Exploration
Vision transformers (ViTs) are quickly becoming the de-facto architectur...
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...
research
∙
11/28/2022
Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers
Deep neural networks are susceptible to shortcut learning, using simple ...
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...
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...
research
∙
10/19/2022
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
As industrial applications are increasingly automated by machine learnin...
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...
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...
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 ...
research
∙
10/06/2022
The Lie Derivative for Measuring Learned Equivariance
Equivariance guarantees that a model's predictions capture key symmetrie...
research
∙
08/19/2022
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Standard diffusion models involve an image transform – adding Gaussian n...
research
∙
06/08/2022
Autoregressive Perturbations for Data Poisoning
The prevalence of data scraping from social media as a means to obtain d...
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...
research
∙
04/19/2022
Poisons that are learned faster are more effective
Imperceptible poisoning attacks on entire datasets have recently been to...
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...
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...
research
∙
02/23/2022
Bayesian Model Selection, the Marginal Likelihood, and Generalization
How do we compare between hypotheses that are entirely consistent with o...
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...
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...
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...
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 ...
research
∙
11/25/2021
Active Learning at the ImageNet Scale
Active learning (AL) algorithms aim to identify an optimal subset of dat...
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...
research
∙
10/15/2021
Comparing Human and Machine Bias in Face Recognition
Much recent research has uncovered and discussed serious concerns of bia...
research
∙
10/13/2021
Identification of Attack-Specific Signatures in Adversarial Examples
The adversarial attack literature contains a myriad of algorithms for cr...
research
∙
09/29/2021
Stochastic Training is Not Necessary for Generalization
It is widely believed that the implicit regularization of stochastic gra...
research
∙
09/09/2021
Towards Transferable Adversarial Attacks on Vision Transformers
Vision transformers (ViTs) have demonstrated impressive performance on a...
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...
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...
research
∙
06/21/2021
Adversarial Examples Make Strong Poisons
The adversarial machine learning literature is largely partitioned into ...
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...
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...
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...
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...
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...
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...
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...
research
∙
02/22/2021