113 citations · 169 across the 14 of their papers we have counts for
14 papers
Is Certifying Robustness Still Worthwhile?
Ravi Mangal, Klas Leino, Zifan Wang +5
Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilit…
A Recipe for Improved Certifiable Robustness
Kai Hu, Klas Leino, Zifan Wang +1
Recent studies have highlighted the potential of Lipschitz-based methods for training certifiably robust neural networks against adversarial attacks. A key challenge, supported bot…
Limitations of Piecewise Linearity for Efficient Robustness Certification
Klas Leino
Certified defenses against small-norm adversarial examples have received growing attention in recent years; though certified accuracies of state-of-the-art methods remain far below…
Unlocking Deterministic Robustness Certification on ImageNet
Kai Hu, Andy Zou, Zifan Wang +2
Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolu…
On the Perils of Cascading Robust Classifiers
Ravi Mangal, Zifan Wang, Chi Zhang +3
Ensembling certifiably robust neural networks is a promising approach for improving the \emph{certified robust accuracy} of neural models. Black-box ensembles that assume only quer…
Selective Ensembles for Consistent Predictions
Emily Black, Klas Leino, Matt Fredrikson
Recent work has shown that models trained to the same objective, and which achieve similar measures of accuracy on consistent test data, may nonetheless behave very differently on…
Self-Correcting Neural Networks For Safe Classification
Klas Leino, Aymeric Fromherz, Ravi Mangal +3
Classifiers learnt from data are increasingly being used as components in systems where safety is a critical concern. In this work, we present a formal notion of safety for classif…
Relaxing Local Robustness
Klas Leino, Matt Fredrikson
Certifiable local robustness, which rigorously precludes small-norm adversarial examples, has received significant attention as a means of addressing security concerns in deep lear…
Globally-Robust Neural Networks
Klas Leino, Zifan Wang, Matt Fredrikson
The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We…
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models
Kaiji Lu, Piotr Mardziel, Klas Leino +2
LSTM-based recurrent neural networks are the state-of-the-art for many natural language processing (NLP) tasks. Despite their performance, it is unclear whether, or how, LSTMs lear…
Fast Geometric Projections for Local Robustness Certification
Aymeric Fromherz, Klas Leino, Matt Fredrikson +2
Local robustness ensures that a model classifies all inputs within an -ball consistently, which precludes various forms of adversarial inputs. In this paper, we present a f…
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
Klas Leino, Matt Fredrikson
Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we…
Feature-Wise Bias Amplification
Klas Leino, Emily Black, Matt Fredrikson +2
We study the phenomenon of bias amplification in classifiers, wherein a machine learning model learns to predict classes with a greater disparity than the underlying ground truth.…
Influence-Directed Explanations for Deep Convolutional Networks
Klas Leino, Shayak Sen, Anupam Datta +2
We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peerin…