Search Results for author:
Found 22 papers, 7 papers with code
Generating Programmatic Referring Expressions via Program Synthesis
The policy neural network employs a program interpreter that provides immediate feedback on the consequences of the decisions made by the policy, and also takes into account the uncertainty in the symbolic representation of the image.
Verified Training for Counterfactual Explanation Robustness under Data Shift
Our empirical evaluation demonstrates that VeriTraCER generates CEs that (1) are verifiably robust to small model updates and (2) display competitive robustness to state-of-the-art approaches in handling empirical model updates including random initialization, leave-one-out, and distribution shifts.
The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
We introduce dataset multiplicity, a way to study how inaccuracies, uncertainty, and social bias in training datasets impact test-time predictions.
PECAN: A Deterministic Certified Defense Against Backdoor Attacks
Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model.
AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels
While it has been used successfully in many domains, weak supervision's application scope is limited by the difficulty of constructing labeling functions for domains with complex or high-dimensional features.
Certifying Data-Bias Robustness in Linear Regression
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets.
BagFlip: A Certified Defense against Data Poisoning
Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model.
Certifying Robustness to Programmable Data Bias in Decision Trees
To certify robustness, we use a novel symbolic technique to evaluate a decision-tree learner on a large, or infinite, number of datasets, certifying that each and every dataset produces the same prediction for a specific test point.
Introduction to Neural Network Verification
Deep learning has transformed the way we think of software and what it can do.
Certified Robustness to Programmable Transformations in LSTMs
Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction.
Learning Differentially Private Mechanisms
We demonstrate that our approach is able to learn foundational algorithms from the differential privacy literature and significantly outperforms natural program synthesis baselines.
Generalized Universal Approximation for Certified Networks
To certify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using interval bound propagation.
Interval Universal Approximation for Neural Networks
This is a crucial question, as our constructive proof of IUA is exponential in the size of the approximation domain.
Backdoors in Neural Models of Source Code
Deep neural networks are vulnerable to a range of adversaries.
Robustness to Programmable String Transformations via Augmented Abstract Training
We then present an approach to adversarially training models that are robust to such user-defined string transformations.
Semantic Robustness of Models of Source Code
Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions.
Proving Data-Poisoning Robustness in Decision Trees
Machine learning models are brittle, and small changes in the training data can result in different predictions.
Synthesizing Action Sequences for Modifying Model Decisions
When a model makes a consequential decision, e. g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision.
A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning
Porting code from CPU to GPU is costly and time-consuming; Unless much time is invested in development and optimization, it is not obvious, a priori, how much speed-up is achievable or how much room is left for improvement.
Neural-Augmented Static Analysis of Android Communication
We address the problem of discovering communication links between applications in the popular Android mobile operating system, an important problem for security and privacy in Android.
Quantifying Program Bias
With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate whether programs are biased.
Fairness as a Program Property
We explore the following question: Is a decision-making program fair, for some useful definition of fairness?
