arXiv subjects

Saeid Tizpaz-Niari

Publications and source records attributed to Saeid Tizpaz-Niari.

At least 19 recordsLinked to original sources

arXiv2026

FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software

Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before assessing bias. We present FairLint-DL, a Visual Studio Code extension that implements a shift-left approach to fairness testing by enabling pre-training, IDE-native bias detection directly on tabular datasets. FairLint-DL trains a configurable deep neural network as a proxy model and applies information-theoretic Quantitative Individual Discrimination (QID) metrics. Grounded in Shannon and min-entropy, QID quantifies the causal influence of protected attributes on predictions. The system implements a two-phase gradient-guided search algorithm for discovering discriminatory instances, a causal debugging pipeline that localizes bias to specific network layers and neurons via sensitivity analysis, and dual explainability engines using SHAP and LIME for feature-level attribution. Evaluation on three tabular benchmarks (Adult Census Income, German Credit, and Bank Marketing) reveals fairness concerns that vary widely across datasets: on Adult, 96.0% of analyzed instances exhibit QID above the 0.1-bit significance threshold, with a mean QID of 0.619 bits and a disparate impact ratio of 0.581, violating the four-fifths legal rule. FairLint-DL produces these results within 12 seconds on cached models, demonstrating the feasibility of integrating fairness analysis into the developer workflow without significant overhead.

cs.SE↗

arXiv2026

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust

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 checks low-level memory safety and termination on eBPF programs, but it does not enforce many higher-level source-level properties, such as initialization discipline, schema consistency, or error handling. We document nine classes of source-level bugs that compile, pass the kernel verifier, and can silently corrupt data, leak kernel memory to userspace, or yield incorrect enforcement outcomes. To harden such verifier-accepted buggy programs and support safe migration, we present Heimdall, an automated pipeline that uses large language models to translate legacy libbpf C programs to Aya Rust. Heimdall iteratively repairs compilation and kernel-verifier failures, rejects unsafe escape hatches in Rust-Aya with a static analysis safety engine, and proves per-program equivalence to the original via symbolic execution and Z3-based equivalence checking. Across 115 eBPF programs, Heimdall generates 109 formally proven-equivalent translations (94.8%). In the process, Heimdall identifies nine bugs in real-world eBPF programs and fixes all of them, two of which leak randomized kernel addresses to userspace and break KASLR. Eight of the nine have also been acknowledged and fixed upstream by the developers. Heimdall is the first system to automate memory-safe-language migration of production eBPF programs with per-program formal guarantees that the migration preserves observable behavior.

cs.CR↗

arXiv2026

Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs

Data-driven software systems are increasingly deployed in high-stakes socio-economic domains, from criminal justice to financial lending. However, these systems often exhibit individual discrimination---unjustified disparities in which a program yields different outcomes for similar individuals who differ only in their protected attributes (e.g., race, gender, age). While existing research has focused on detecting and quantifying these bugs, there remains a critical lack of principled mechanisms to explain and localize individual fairness bugs. Current explanation techniques are largely designed for single-input decisions rather than the relational nature of discrimination, which inherently involves a comparison between an original and a counterfactual pair. We present REMI, a framework for the automated localization, explanation, and mitigation of individual discrimination. Inspired by loop-invariant synthesis in formal methods, we treat counterfactual fairness as a relational invariant discovery problem. We introduce a bidirectional relational explanation framework that learns over paired examples $(x, x')$ to identify regions of the input space where fairness is violated. Unlike traditional one-way implication pairs used in invariant inference, our approach enforces bidirectional constraints: requiring identical outcomes for both original and counterfactual samples. REMI utilizes three data-alignment techniques to infer interpretable rule-based models that act as "fairness invariants." These rules serve as guardrails to selectively block or relabel unfair predictions without requiring model retraining. Our evaluation on symbolic and neural network programs demonstrates that REMI localizes ground-truth fairness bugs in over 83% of cases, significantly outperforming state-of-the-art baselines and reducing discriminatory decisions in black-box models by up to 70%.

cs.SE↗

arXiv2026

An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Software

Large language models (LLMs) show promise for translating natural-language statutes into executable logic, but reliability in legally critical settings remains challenging due to ambiguity and hallucinations. We present an agentic approach for developing legal-critical software, using U.S. federal tax preparation as a case study. The key challenge is test-case generation under the oracle problem, where correct outputs require interpreting law. Building on metamorphic testing, we introduce higher-order metamorphic relations that compare system outputs across structured shifts among similar individuals. Because authoring such relations is tedious and error-prone, we use an LLM-driven, role-based framework to automate test generation and code synthesis. We implement a multi-agent system that translates tax code into executable software and incorporates a metamorphic-testing agent that searches for counterexamples. In experiments, our framework using a smaller model (GPT-4o-mini) achieves a worst-case pass rate of 45%, outperforming frontier models (GPT-4o and Claude 3.5, 9-15%) on complex tax-code tasks. These results support agentic LLM methodologies as a path to robust, trustworthy legal-critical software from natural-language specifications.

cs.SE↗

arXiv2026

On the Robustness of Fairness Practices: A Causal Framework for Systematic Evaluation

Machine learning (ML) algorithms are increasingly deployed to make critical decisions in socioeconomic applications such as finance, criminal justice, and autonomous driving. However, due to their data-driven and pattern-seeking nature, ML algorithms may develop decision logic that disproportionately distributes opportunities, benefits, resources, or information among different population groups, potentially harming marginalized communities. In response to such fairness concerns, the software engineering and ML communities have made significant efforts to establish the best practices for creating fair ML software. These include fairness interventions for training ML models, such as including sensitive features, selecting non-sensitive attributes, and applying bias mitigators. But how reliably can software professionals tasked with developing data-driven systems depend on these recommendations? And how well do these practices generalize in the presence of faulty labels, missing data, or distribution shifts? These questions form the core theme of this paper.

cs.SE↗

arXiv2025

Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations

Fairness in algorithmic decision-making is often framed in terms of individual fairness, which requires that similar individuals receive similar outcomes. A system violates individual fairness if there exists a pair of inputs differing only in protected attributes (such as race or gender) that lead to significantly different outcomes-for example, one favorable and the other unfavorable. While this notion highlights isolated instances of unfairness, it fails to capture broader patterns of systematic or clustered discrimination that may affect entire subgroups. We introduce and motivate the concept of discrimination clustering, a generalization of individual fairness violations. Rather than detecting single counterfactual disparities, we seek to uncover regions of the input space where small perturbations in protected features lead to k-significantly distinct clusters of outcomes. That is, for a given input, we identify a local neighborhood-differing only in protected attributes-whose members' outputs separate into many distinct clusters. These clusters reveal significant arbitrariness in treatment solely based on protected attributes that help expose patterns of algorithmic bias that elude pairwise fairness checks. We present HyFair, a hybrid technique that combines formal symbolic analysis (via SMT and MILP solvers) to certify individual fairness with randomized search to discover discriminatory clusters. This combination enables both formal guarantees-when no counterexamples exist-and the detection of severe violations that are computationally challenging for symbolic methods alone. Given a set of inputs exhibiting high k-unfairness, we introduce a novel explanation method to generate interpretable, decision-tree-style artifacts. Our experiments demonstrate that HyFair outperforms state-of-the-art fairness verification and local explanation methods.

cs.SE↗

arXiv2025

Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing

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 sensitive social contexts where fairness concerns become especially crucial. Since LLMs develop decision-making patterns by training on massive datasets of human-generated content, they naturally encode and perpetuate societal biases. While modifying training datasets and algorithms is expensive and requires significant resources; post-processing techniques-such as selectively deactivating neurons and attention heads in pre-trained LLMs-can provide feasible and effective approaches to improve fairness. However, identifying the optimal subset of parameters to prune presents a combinatorial challenge within LLMs' immense parameter space, requiring solutions that efficiently balance competing objectives across the frontiers of model fairness and utility. To address the computational challenges, we explore a search-based program repair approach via randomized simulated annealing. Given the prohibitive evaluation costs in billion-parameter LLMs, we develop surrogate deep neural networks that efficiently model the relationship between attention head states (active/inactive) and their corresponding fairness/utility metrics. This allows us to perform optimization over the surrogate models and efficiently identify optimal subsets of attention heads for selective pruning rather than directly searching through the LLM parameter space. 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. Our experiments show that Attention Pruning achieves up to $40\%$ reduction in gender bias and outperforms the state-of-the-art bias mitigation strategies.

cs.AI↗

arXiv2025

Risk Estimation in Differential Fuzzing via Extreme Value Theory

Differential testing is a highly effective technique for automatically detecting software bugs and vulnerabilities when the specifications involve an analysis over multiple executions simultaneously. Differential fuzzing, in particular, operates as a guided randomized search, aiming to find (similar) inputs that lead to a maximum difference in software outputs or their behaviors. However, fuzzing, as a dynamic analysis, lacks any guarantees on the absence of bugs: from a differential fuzzing campaign that has observed no bugs (or a minimal difference), what is the risk of observing a bug (or a larger difference) if we run the fuzzer for one or more steps? This paper investigates the application of Extreme Value Theory (EVT) to address the risk of missing or underestimating bugs in differential fuzzing. The key observation is that differential fuzzing as a random process resembles the maximum distribution of observed differences. Hence, EVT, a branch of statistics dealing with extreme values, is an ideal framework to analyze the tail of the differential fuzzing campaign to contain the risk. We perform experiments on a set of real-world Java libraries and use differential fuzzing to find information leaks via side channels in these libraries. We first explore the feasibility of EVT for this task and the optimal hyperparameters for EVT distributions. We then compare EVT-based extrapolation against baseline statistical methods like Markov's as well as Chebyshev's inequalities, and the Bayes factor. EVT-based extrapolations outperform the baseline techniques in 14.3% of cases and tie with the baseline in 64.2% of cases. Finally, we evaluate the accuracy and performance gains of EVT-enabled differential fuzzing in real-world Java libraries, where we reported an average saving of tens of millions of bytecode executions by an early stop.

cs.SE↗

arXiv2025

Technical Challenges in Maintaining Tax Prep Software with Large Language Models

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. The dynamic nature of tax regulations poses a significant challenge to accurately and timely maintaining tax software artifacts. The state-of-the-art in maintaining tax prep software is time-consuming and error-prone as it involves manual code analysis combined with an expert interpretation of tax law amendments. We posit that the rigor and formality of tax amendment language, as expressed in IRS publications, makes it amenable to automatic translation to executable specifications (code). Our research efforts focus on identifying, understanding, and tackling technical challenges in leveraging Large Language Models (LLMs), such as ChatGPT and Llama, to faithfully extract code differentials from IRS publications and automatically integrate them with the prior version of the code to automate tax prep software maintenance.

cs.SE↗

arXiv2025

Fairness Testing through Extreme Value Theory

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, it can encode or amplify discriminatory practices. Previous research on algorithmic fairness has focused on improving average-case fairness. On the other hand, fairness at the extreme ends of the spectrum, which often signifies lasting and impactful shifts in societal attitudes, has received significantly less emphasis. Leveraging the statistics of extreme value theory (EVT), we propose a novel fairness criterion called extreme counterfactual discrimination (ECD). This criterion estimates the worst-case amounts of disadvantage in outcomes for individuals solely based on their memberships in a protected group. Utilizing tools from search-based software engineering and generative AI, we present a randomized algorithm that samples a statistically significant set of points from the tail of ML outcome distributions even if the input dataset lacks a sufficient number of relevant samples. We conducted several experiments on four ML models (deep neural networks, logistic regression, and random forests) over 10 socially relevant tasks from the literature on algorithmic fairness. First, we evaluate the generative AI methods and find that they generate sufficient samples to infer valid EVT distribution in 95% of cases. Remarkably, we found that the prevalent bias mitigators reduce the average-case discrimination but increase the worst-case discrimination significantly in 5% of cases. We also observed that even the tail-aware mitigation algorithm -- MiniMax-Fairness -- increased the worst-case discrimination in 30% of cases. We propose a novel ECD-based mitigator that improves fairness in the tail in 90% of cases with no degradation of the average-case discrimination.

cs.SE↗

arXiv2024

FairLay-ML: Intuitive Debugging of Fairness in Data-Driven Social-Critical Software

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 solutions, however, pose major threats to the trustworthiness of automated decision-support software. A diminished understanding of the solution by the developer and historical/current biases in the data sets are primary challenges. 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. FairLay-ML visualizes the logic of datasets, trained models, and decisions for a given data point. In addition, it trains various models with varying fairness-accuracy trade-offs. Crucially, FairLay-ML incorporates counterfactual fairness testing that finds bugs beyond the development datasets. We conducted two studies through FairLay-ML that allowed us to measure false positives/negatives in prevalent counterfactual testing and understand the human perception of counterfactual test cases in a class survey. FairLay-ML and its benchmarks are publicly available at https://github.com/Pennswood/FairLay-ML. The live version of the tool is available at https://fairlayml-v2.streamlit.app/. We provide a video demo of the tool at https://youtu.be/wNI9UWkywVU?t=133.

cs.SE↗

arXiv2024

Probabilistic Guarantees for Practical LIA Loop Invariant Automation

Despite the crucial need for formal safety and security verification of programs, discovering loop invariants remains a significant challenge. Static analysis is a primary technique for inferring loop invariants but often relies on substantial assumptions about underlying theories. Data-driven methods supported by dynamic analysis and machine learning algorithms have shown impressive performance in inferring loop invariants for some challenging programs. However, state-of-the-art data-driven techniques do not offer theoretical guarantees for finding loop invariants. We present a novel technique that leverages the simulated annealing (SA) search algorithm combined with SMT solvers and computational geometry to provide probabilistic guarantees for inferring loop invariants using data-driven methods. Our approach enhances the SA search with real analysis to define the search space and employs parallelism to increase the probability of success. To ensure the convergence of our algorithm, we adapt e-nets, a key concept from computational geometry. Our tool, DLIA2, implements these algorithms and demonstrates competitive performance against state-of-the-art techniques. We also identify a subclass of programs, on which we outperform the current state-of-the-art tool GSpacer.

cs.PL↗

arXiv2024

Metamorphic Debugging for Accountable Software

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-economic and legally critical implications, ensuring software accountability -- encompassing qualities such as legal compliance, explainability, perceptions of procedural justice, fairness of outcomes, and confidentiality/privacy -- is of paramount social importance. Moreover, software that accurately interprets its requirements, complies with legal standards and upholds social fairness can serve as a surrogate for legal and social norms, enabling policymakers to inquire about the law as seamlessly as a software engineer conducts a test. However, ensuring software accountability faces three key challenges: i) Translating legalese into formal specifications, ii) Lack of a definitive 'truth' for queries (the oracle problem), and iii) Scarcity of trustworthy datasets due to privacy and legal concerns. Drawing from the experiences in debugging U.S. tax preparation software, we propose that these challenges can be tackled by focusing on relational specifications. While the exact output for a given input may be unknown, the relationship between the outputs of two related inputs may be easier to express. This observation resembles i) the legal doctrine of precedent, meaning that similar cases must yield similar rulings; and ii) metamorphic relation (MR) in software engineering that requires a specific relation between software inputs and outputs. We propose metamorphic debugging as the foundation for detecting, explaining, and repairing socio-legal software for these relations. We showcase recent results that leverage metamorphic debugging to detect and explain accountability bugs in tax prep and poverty management software systems.

cs.SE↗

arXiv2024

NeuFair: Neural Network Fairness Repair with Dropout

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 critical domains with significant fairness implications. While neural networks are exceptionally good at finding statistical patterns from data, they may encode and amplify existing biases from the historical data. Existing bias mitigation algorithms often require modifying the input dataset or the learning algorithms. We posit that the prevalent dropout methods that prevent over-fitting during training by randomly dropping neurons may be an effective and less intrusive approach to improve the fairness of pre-trained DNNs. However, finding the ideal set of neurons to drop is a combinatorial problem. We propose NeuFair, a family of post-processing randomized algorithms that mitigate unfairness in pre-trained DNNs via dropouts during inference after training. Our randomized search is guided by an objective to minimize discrimination while maintaining the model's utility. 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. We provide intuitive explanations of these phenomena and carefully examine the influence of various hyperparameters of search algorithms on the results. Finally, we empirically and conceptually compare NeuFair to different state-of-the-art bias mitigators.

cs.LG↗

arXiv2024

Predicting Fairness of ML Software Configurations

This paper investigates the relationships between hyperparameters of machine learning and fairness. Data-driven solutions are increasingly used in critical socio-technical applications where ensuring fairness is important. Rather than explicitly encoding decision logic via control and data structures, the ML developers provide input data, perform some pre-processing, choose ML algorithms, and tune hyperparameters (HPs) to infer a program that encodes the decision logic. Prior works report that the selection of HPs can significantly influence fairness. However, tuning HPs to find an ideal trade-off between accuracy, precision, and fairness has remained an expensive and tedious task. Can we predict fairness of HP configuration for a given dataset? Are the predictions robust to distribution shifts? We focus on group fairness notions and investigate the HP space of 5 training algorithms. We first find that tree regressors and XGBoots significantly outperformed deep neural networks and support vector machines in accurately predicting the fairness of HPs. When predicting the fairness of ML hyperparameters under temporal distribution shift, the tree regressors outperforms the other algorithms with reasonable accuracy. However, the precision depends on the ML training algorithm, dataset, and protected attributes. For example, the tree regressor model was robust for training data shift from 2014 to 2018 on logistic regression and discriminant analysis HPs with sex as the protected attribute; but not for race and other training algorithms. Our method provides a sound framework to efficiently perform fine-tuning of ML training algorithms and understand the relationships between HPs and fairness.

cs.SE↗

arXiv2024

Worst-Case Convergence Time of ML Algorithms via Extreme Value Theory

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 systems, and providing the worst-case converge times is essential to guarantee the availability of ML and its services. However, timing properties such as worst-case convergence times (WCCT) are difficult to verify since (1) they are not encoded in the syntax or semantics of underlying programming languages of AI, (2) their evaluations depend on both algorithmic implementations and underlying systems, and (3) their measurements involve uncertainty and noise. Therefore, prevalent formal methods and statistical models fail to provide rich information on the amounts and likelihood of WCCT. Our key observation is that the timing information we seek represents the extreme tail of execution times. Therefore, extreme value theory (EVT), a statistical discipline that focuses on understanding and predicting the distribution of extreme values in the tail of outcomes, provides an ideal framework to model and analyze WCCT in the training and inference phases of ML paradigm. Building upon the mathematical tools from EVT, we propose a practical framework to predict the worst-case timing properties of ML. Over a set of linear ML training algorithms, we show that EVT achieves a better accuracy for predicting WCCTs than relevant statistical methods such as the Bayesian factor. 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.

cs.SE↗

arXiv2023

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. According to the U.S. Internal Revenue Service (IRS), in FY22, nearly 50% of taxpayers filed their individual income taxes using tax software. Given the legal consequences of incorrectly filing taxes for the taxpayer, ensuring the correctness of tax software is of paramount importance. Metamorphic testing has emerged as a leading solution to test and debug legal-critical tax software due to the absence of correctness requirements and trustworthy datasets. The key idea behind metamorphic testing is to express the properties of a system in terms of the relationship between one input and its slightly metamorphosed twinned input. Extracting metamorphic properties from IRS tax publications is a tedious and time-consuming process. As a response, this paper formulates the task of generating metamorphic specifications as a translation task between properties extracted from tax documents - expressed in natural language - to a contrastive first-order logic form. We perform a systematic analysis on the potential and limitations of in-context learning with Large Language Models(LLMs) for this task, and outline a research agenda towards automating the generation of metamorphic specifications for tax preparation software.

cs.SE↗

arXiv2023

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. Machine learning models trained on datasets biased against minority groups are increasingly used to guide life-altering social decisions, prompting the urgent need to study their logic for unfairness. Due to this problem's impact on vast populations of the general public, it is critical for the layperson -- not just subject matter experts in social justice or machine learning experts -- to understand the nature of unfairness within these algorithms and the potential trade-offs. Existing research on fairness in machine learning focuses mostly on the mathematical definitions and tools to understand and remedy unfair models, with some directly citing user-interactive tools as necessary for future work. This thesis presents FairLay-ML, a proof-of-concept GUI integrating some of the most promising tools to provide intuitive explanations for unfair logic in ML models by integrating existing research tools (e.g. Local Interpretable Model-Agnostic Explanations) with existing ML-focused GUI (e.g. Python Streamlit). We test FairLay-ML using models of various accuracy and fairness generated by an unfairness detector tool, Parfait-ML, and validate our results using Themis. Our study finds that the technology stack used for FairLay-ML makes it easy to install and provides real-time black-box explanations of pre-trained models to users. Furthermore, the explanations provided translate to actionable remedies.

cs.LG↗