1.5k citations · 3.3k across the 15 of their papers we have counts for
16 papers
How to Secure Existing C and C++ Software without Memory Safety
Úlfar Erlingsson
The most important security benefit of software memory safety is easy to state: for C and C++ software, attackers can exploit most bugs and vulnerabilities to gain full, unfettered…
Extracting Training Data from Large Language Models
Nicholas Carlini, Florian Tramer, Eric Wallace +9
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary ca…
Tempered Sigmoid Activations for Deep Learning with Differential Privacy
Nicolas Papernot, Abhradeep Thakurta, Shuang Song +2
Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer privacy for training data. In practice, this has been mostly an aftertho…
Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation
Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov +4
Recently, a number of approaches and techniques have been introduced for reporting software statistics with strong privacy guarantees. These range from abstract algorithms to compr…
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…
That which we call private
Úlfar Erlingsson, Ilya Mironov, Ananth Raghunathan +1
The guarantees of security and privacy defenses are often strengthened by relaxing the assumptions made about attackers or the context in which defenses are deployed. Such relaxati…