45 citations · 67 across the 22 of their papers we have counts for
27 papers
FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software
Archit Rathod, Saeid Tizpaz-Niari
Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before asses…
Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs
Ranit Debnath Akash, Ashish Kumar, Gang Tan +1
Data-driven software systems are increasingly deployed in high-stakes socio-economic domains, from criminal justice to financial lending. However, these systems often exhibit indiv…
Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust
Vishnu Asutosh Dasu, Monika Santra, Md Rafi Ur Rashid +3
Extended Berkeley Packet Filter (eBPF) programs are kernel extensions used for networking, observability, and security enforcement in the Linux kernel. The in-kernel eBPF verifier…
On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation
Verya Monjezi, Ashish Kumar, Ashutosh Trivedi +2
Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. Howev…
Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations
Ranit Debnath Akash, Ashish Kumar, Verya Monjezi +4
Fairness in algorithmic decision-making is often framed in terms of individual fairness, which requires that similar individuals receive similar outcomes. A system violates individ…
An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software
Sina Gogani-Khiabani, Ashutosh Trivedi, Diptikalyan Saha +1
Large language models (LLMs) show promise for translating natural-language statutes into executable logic, but reliability in legally critical settings remains challenging due to a…
Technical Challenges in Maintaining Tax Prep Software with Large Language Models
Sina Gogani-Khiabani, Varsha Dewangan, Nina Olson +2
As the US tax law evolves to adapt to ever-changing politico-economic realities, tax preparation software plays a significant role in helping taxpayers navigate these complexities.…
Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing
Vishnu Asutosh Dasu, Md Rafi ur Rashid, Vipul Gupta +2
This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitiv…
Fairness Testing through Extreme Value Theory
Verya Monjezi, Ashutosh Trivedi, Vladik Kreinovich +1
Data-driven software is increasingly being used as a critical component of automated decision-support systems. Since this class of software learns its logic from historical data, i…
Probabilistic Guarantees for Practical LIA Loop Invariant Automation
Ashish Kumar, Jilaun Zhang, Saeid Tizpaz-Niari +1
Despite the crucial need for formal safety and security verification of programs, discovering loop invariants remains a significant challenge. Static analysis is a primary techniqu…
Metamorphic Debugging for Accountable Software
Saeid Tizpaz-Niari, Shiva Darian, Ashutosh Trivedi
As the laws have become more complicated and enormous, the role of software systems in navigating and understanding these intricacies has become more critical. Given their socio-ec…
NeuFair: Neural Network Fairness Repair with Dropout
Vishnu Asutosh Dasu, Ashish Kumar, Saeid Tizpaz-Niari +1
This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially c…
FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software
Normen Yu, Luciana Carreon, Gang Tan +1
Data-driven software solutions have significantly been used in critical domains with significant socio-economic, legal, and ethical implications. The rapid adoptions of data-driven…
Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory
Saeid Tizpaz-Niari, Sriram Sankaranarayanan
This paper leverages the statistics of extreme values to predict the worst-case convergence times of machine learning algorithms. Timing is a critical non-functional property of ML…
Predicting Fairness of ML Software Configurations
Salvador Robles Herrera, Verya Monjezi, Vladik Kreinovich +2
This paper investigates the relationships between hyperparameters of machine learning and fairness. Data-driven solutions are increasingly used in critical socio-technical applicat…
On the Potential and Limitations of Few-Shot In-Context Learning to Generate Metamorphic Specifications for Tax Preparation Software
Dananjay Srinivas, Rohan Das, Saeid Tizpaz-Niari +2
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 softwar…
FairLay-ML: Intuitive Remedies for Unfairness in Data-Driven Social-Critical Algorithms
Normen Yu, Gang Tan, Saeid Tizpaz-Niari
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…
Over-Measurement Paradox: Suspension of Thermonuclear Research Center and Need to Update Standards
Hector Reyes, Saeid Tizpaz-Niari, Vladik Kreinovich
In general, the more measurements we perform, the more information we gain about the system and thus, the more adequate decisions we will be able to make. However, in situations wh…
Information-Theoretic Testing and Debugging of Fairness Defects in Deep Neural Networks
Verya Monjezi, Ashutosh Trivedi, Gang Tan +1
The deep feedforward neural networks (DNNs) are increasingly deployed in socioeconomic critical decision support software systems. DNNs are exceptionally good at finding minimal, s…
Metamorphic Testing and Debugging of Tax Preparation Software
Saeid Tizpaz-Niari, Verya Monjezi, Morgan Wagner +3
This paper presents a data-driven framework to improve the trustworthiness of US tax preparation software systems. Given the legal implications of bugs in such software on its user…
Fairness-aware Configuration of Machine Learning Libraries
Saeid Tizpaz-Niari, Ashish Kumar, Gang Tan +1
This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-c…
Detecting and Understanding Real-World Differential Performance Bugs in Machine Learning Libraries
Saeid Tizpaz-Niari, Pavol Cerný, Ashutosh Trivedi
Programming errors that degrade the performance of systems are widespread, yet there is little tool support for analyzing these bugs. We present a method based on differential perf…
Efficient Detection and Quantification of Timing Leaks with Neural Networks
Saeid Tizpaz-Niari, Pavol Cerny, Sriram Sankaranarayanan +1
Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach f…
Quantitative Mitigation of Timing Side Channels
Saeid Tizpaz-Niari, Pavol Cerny, Ashutosh Trivedi
Timing side channels pose a significant threat to the security and privacy of software applications. We propose an approach for mitigating this problem by decreasing the strength o…