Search Results for author:
Found 16 papers, 4 papers with code
Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing
This paper introduces Attention Pruning, a fairness-aware surrogate simulated annealing approach to prune attention heads in LLMs that disproportionately contribute to bias while minimally impacting overall model utility.
Fairness Testing through Extreme Value Theory
Previous research on algorithmic fairness has focused on improving average-case fairness.
NeuFair: Neural Network Fairness Repair with Dropout
We show that our design of randomized algorithms is effective and efficient in improving fairness (up to 69%) with minimal or no model performance degradation.
FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software
To aid data-driven software developers and end-users, we present FairLay-ML, a debugging tool to test and explain the fairness implications of data-driven solutions.
Predicting Fairness of ML Software Configurations
However, the precision depends on the ML training algorithm, dataset, and protected attributes.
Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory
On the set of larger machine learning training algorithms and deep neural network inference, we show the feasibility and usefulness of EVT models to accurately predict WCCTs, their expected return periods, and their likelihood.
On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software
Due to the ever-increasing complexity of income tax laws in the United States, the number of US taxpayers filing their taxes using tax preparation software (henceforth, tax software) continues to increase.
FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms
This thesis explores open-sourced machine learning (ML) model explanation tools to understand whether these tools can allow a layman to visualize, understand, and suggest intuitive remedies to unfairness in ML-based decision-support systems.
Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks
Guided by the quantitative fairness, we present a causal debugging framework to localize inadequately trained layers and neurons responsible for fairness defects.
Fairness-aware Configuration of Machine Learning Libraries
This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs.
Detecting and Understanding Real-World Differential Performance Bugs in Machine Learning Libraries
On a set of micro-benchmarks, we show that our approach outperforms state-of-the-art fuzzers in finding inputs to characterize the differential performance.
Efficient Detection and Quantification of Timing Leaks with Neural Networks
As demonstrated in our experiments, both of these tasks are feasible in practice --- making the approach a significant improvement over the state-of-the-art side channel detectors and quantifiers.
Quantitative Mitigation of Timing Side Channels
In contrast to the existing mitigation approaches, we show that in the functional-observation threat model, SCHMIT is scalable and able to maximize confidentiality under the performance overhead bound.
Data-Driven Debugging for Functional Side Channels
On the realistic programs, we show the scalability of FUCHSIA in analyzing functional side channels in Java programs with thousands of methods.
Differential Performance Debugging with Discriminant Regression Trees
We propose a data-driven technique based on discriminant regression tree (DRT) learning problem where the goal is to discriminate among different classes of inputs.
Discriminating Traces with Time
What properties about the internals of a program explain the possible differences in its overall running time for different inputs?
