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
∙
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
∙
07/16/2022
Certified Neural Network Watermarks with Randomized Smoothing
Watermarking is a commonly used strategy to protect creators' rights to ...
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
∙
11/25/2021
Active Learning at the ImageNet Scale
Active learning (AL) algorithms aim to identify an optimal subset of dat...
research
∙
06/21/2021
Adversarial Examples Make Strong Poisons
The adversarial machine learning literature is largely partitioned into ...
research
∙
02/16/2021
Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
Large organizations such as social media companies continually release d...
research
∙
10/13/2020
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
The design of revenue-maximizing auctions with strong incentive guarante...
research
∙
07/07/2020
Detection as Regression: Certified Object Detection by Median Smoothing
Despite the vulnerability of object detectors to adversarial attacks, ve...
research
∙
06/15/2020
Certifying Strategyproof Auction Networks
Optimal auctions maximize a seller's expected revenue subject to individ...
research
∙
03/14/2020
Certified Defenses for Adversarial Patches
Adversarial patch attacks are among one of the most practical threat mod...
research
∙
02/22/2020
Improving the Tightness of Convex Relaxation Bounds for Training Certifiably Robust Classifiers
Convex relaxations are effective for training and certifying neural netw...
research
∙
11/18/2019
WITCHcraft: Efficient PGD attacks with random step size
State-of-the-art adversarial attacks on neural networks use expensive it...
research
∙
02/01/2019