activity
20162024
most citedOn Evaluating Adversarial Robustness

579 citations · 1.2k across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG2023

Training Private Models That Know What They Don't Know

Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta +2

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning h…

cs.LG20225 cited

Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search

Yannis Cattan, Christopher A. Choquette-Choo, Nicolas Papernot +1

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algo…

cs.LG20217 cited

Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

Milad Nasr, Shuang Song, Abhradeep Thakurta +2

Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, wh…

cs.LG2020

Data-Free Model Extraction

Jean-Baptiste Truong, Pratyush Maini, Robert J. Walls +1

Current model extraction attacks assume that the adversary has access to a surrogate dataset with characteristics similar to the proprietary data used to train the victim model. Th…

cs.LG2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Florian Tramèr, Jens Behrmann, Nicholas Carlini +2

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an in…

cs.LG201919 cited

Distribution Density, Tails, and Outliers in Machine Learning: Metrics and Applications

Nicholas Carlini, Úlfar Erlingsson, Nicolas Papernot

We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples…