Ashutosh Gupta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ashutosh Gupta has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- S. Akshay
Indian Institute of Technology Bombay
3 shared publications - Shankara Narayanan Krishna
Indian Institute of Technology Bombay
3 shared publications - Divyesh Unadkat
Indian Institute of Technology Bombay
2 shared publications - Kaushik Mallik
IMDEA Software Institute
2 shared publications - Mohammad Afzal
Indian Institute of Technology Bombay Mumbai India
2 shared publications - Omkar Tuppe
IIT Bombay
2 shared publications
Latest Publications
- Open Access
- 24 July 2026
- Published by Springer Nature
- p. 551-575
Quantifying Sensitivity for Tree Ensembles: A Symbolic and Compositional Approach
Decision tree ensembles (DTE) are a popular model for a wide range of AI classification tasks, used in multiple safety critical domains, and hence verifying properties on these models has been an active topic of study over the last decade. One such verification question is the problem of sensitivity, which asks, given a DTE, whether a small change in subset of features can lead to misclassification of the input. In this work, our focus is to build a quantitative notion of sensitivity, tailored to DTEs, by discretizing the input space of the model and enumerating the regions which are susceptible to sensitivity. We propose a novel algorithmic technique that can perform this computation efficiently, within a certified error and confidence bound. Our approach is based on encoding the problem as an algebraic decision diagram (ADD), and further splitting it into subproblems that can be solved efficiently and make the computation compositional and scalable. We evaluate the performance of our technique over benchmarks of varying size in terms of number of trees and depth, comparing it against the performance of model counters over the same problem encoding. Experimental results show that our tool $$\textsf{EnSensCount}$$ achieves significant speedup over other approaches and can scale well with the increasing sizes of the ensembles.- 24 July 2026
- Published by Springer Nature
- p. 551-575
Open AccessQuantifying Sensitivity for Tree Ensembles: A Symbolic and Compositional Approach
Decision tree ensembles (DTE) are a popular model for a wide range of AI classification tasks, used in multiple safety critical domains, and hence verifying properties on these models has been an active topic of study over the last decade. One such verification question is the problem of sensitivity, which asks, given a DTE, whether a small change in subset of features can lead to misclassification of the input. In this work, our focus is to build a quantitative notion of sensitivity, tailored to DTEs, by discretizing the input space of the model and enumerating the regions which are susceptible to sensitivity. We propose a novel algorithmic technique that can perform this computation efficiently, within a certified error and confidence bound. Our approach is based on encoding the problem as an algebraic decision diagram (ADD), and further splitting it into subproblems that can be solved efficiently and make the computation compositional and scalable. We evaluate the performance of our technique over benchmarks of varying size in terms of number of trees and depth, comparing it against the performance of model counters over the same problem encoding. Experimental results show that our tool $$\textsf{EnSensCount}$$ achieves significant speedup over other approaches and can scale well with the increasing sizes of the ensembles. - Open Access
- 18 May 2026
- Published by Springer Nature
- p. 480-499
Formal Reasoning About Confidence and Automated Verification of Neural Networks
In the last decade, a large body of work has emerged on robustness of neural networks, i.e., checking if the decision remains unchanged when the input is slightly perturbed. However, most of these approaches ignore the confidence of a neural network on its output. In this work, we aim to develop a generalized framework for formally reasoning about the confidence along with robustness in neural networks. We propose a simple yet expressive grammar that captures various confidence-based specifications. We develop a novel and unified technique to verify all instances of the grammar in a homogeneous way, viz., by adding a few additional layers to the neural network, which enables the use any state-of-the-art neural network verification tool. We perform an extensive experimental evaluation over a large suite of 8870 benchmarks, where the largest network has 138M parameters, and show that this outperforms ad-hoc encoding approaches by a significant margin.
- 18 May 2026
- Published by Springer Nature
- p. 480-499
Open AccessFormal Reasoning About Confidence and Automated Verification of Neural Networks
In the last decade, a large body of work has emerged on robustness of neural networks, i.e., checking if the decision remains unchanged when the input is slightly perturbed. However, most of these approaches ignore the confidence of a neural network on its output. In this work, we aim to develop a generalized framework for formally reasoning about the confidence along with robustness in neural networks. We propose a simple yet expressive grammar that captures various confidence-based specifications. We develop a novel and unified technique to verify all instances of the grammar in a homogeneous way, viz., by adding a few additional layers to the neural network, which enables the use any state-of-the-art neural network verification tool. We perform an extensive experimental evaluation over a large suite of 8870 benchmarks, where the largest network has 138M parameters, and show that this outperforms ad-hoc encoding approaches by a significant margin.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 790-801
Monitoring Robustness and Individual Fairness
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 790-801
Open AccessMonitoring Robustness and Individual Fairness
- Open Access
Glitches in Decision Tree Ensemble Models
Many critical decision-making tasks are now delegated to machine-learned models, and it is imperative that their decisions are trustworthy and reliable, and their outputs are consistent across similar inputs. We identify a new source of unreliable behaviors-called glitches-which may significantly impair the reliability of AI models having steep decision boundaries. Roughly speaking, glitches are small neighborhoods in the input space where the model's output abruptly oscillates with respect to small changes in the input. We provide a formal definition of glitches, and use well-known models and datasets from the literature to demonstrate that they have widespread existence and argue they usually indicate potential model inconsistencies in the neighborhood of where they are found. We proceed to the algorithmic search of glitches for widely used gradient-boosted decision tree (GBDT) models. We prove that the problem of detecting glitches is NP-complete for tree ensembles, already for trees of depth 4. Our glitch-search algorithm for GBDT models uses an MILP encoding of the problem, and its effectiveness and computational feasibility are demonstrated on a set of widely used GBDT benchmarks taken from the literature.
Open AccessGlitches in Decision Tree Ensemble Models
Many critical decision-making tasks are now delegated to machine-learned models, and it is imperative that their decisions are trustworthy and reliable, and their outputs are consistent across similar inputs. We identify a new source of unreliable behaviors-called glitches-which may significantly impair the reliability of AI models having steep decision boundaries. Roughly speaking, glitches are small neighborhoods in the input space where the model's output abruptly oscillates with respect to small changes in the input. We provide a formal definition of glitches, and use well-known models and datasets from the literature to demonstrate that they have widespread existence and argue they usually indicate potential model inconsistencies in the neighborhood of where they are found. We proceed to the algorithmic search of glitches for widely used gradient-boosted decision tree (GBDT) models. We prove that the problem of detecting glitches is NP-complete for tree ensembles, already for trees of depth 4. Our glitch-search algorithm for GBDT models uses an MILP encoding of the problem, and its effectiveness and computational feasibility are demonstrated on a set of widely used GBDT benchmarks taken from the literature.
- 1 February 2025
- Published by Springer Nature
- p. 181-202
Dynamic Partial Order Reduction for Transactional Programs on Serializable Platforms
- 1 February 2025
- Published by Springer Nature
- p. 181-202
Dynamic Partial Order Reduction for Transactional Programs on Serializable Platforms
- 22 October 2023
- Published by Springer Nature
- p. 422-443
Using Counterexamples to Improve Robustness Verification in Neural Networks
- 22 October 2023
- Published by Springer Nature
- p. 422-443
Using Counterexamples to Improve Robustness Verification in Neural Networks
- Open Access
- 22 April 2023
- Published by Springer Nature
- p. 105-125
Optimal Stateless Model Checking for Causal Consistency
We present a framework for efficient stateless model checking (SMC) of concurrent programs under three prominent models of causal consistency, $${\texttt {CCv}}, {\texttt {CM}}, \texttt{CC}$$ . Our approach is based on exploring traces under the program order "Image missing" and the reads from "Image missing" relations. Our SMC algorithm is provably optimal in the sense that it explores each "Image missing" and "Image missing" relation exactly once. We have implemented our framework in a tool called Conschecker . Experiments show that Conschecker performs well in detecting anomalies in classical distributed databases benchmarks.- 22 April 2023
- Published by Springer Nature
- p. 105-125
Open AccessOptimal Stateless Model Checking for Causal Consistency
We present a framework for efficient stateless model checking (SMC) of concurrent programs under three prominent models of causal consistency, $${\texttt {CCv}}, {\texttt {CM}}, \texttt{CC}$$ . Our approach is based on exploring traces under the program order "Image missing" and the reads from "Image missing" relations. Our SMC algorithm is provably optimal in the sense that it explores each "Image missing" and "Image missing" relation exactly once. We have implemented our framework in a tool called Conschecker . Experiments show that Conschecker performs well in detecting anomalies in classical distributed databases benchmarks. - 29 September 2022
- Published by Springer Nature in International Journal on Software Tools for Technology Transfer
- Vol. 24 (5) , 843-888
Full-program induction: verifying array programs sans loop invariants
- 29 September 2022
- Published by Springer Nature in International Journal on Software Tools for Technology Transfer
- Vol. 24 (5) , 843-888
Full-program induction: verifying array programs sans loop invariants
- Open Access
- 17 April 2020
- Published by Springer Nature
- Vol. 12078, 22-39
Verifying Array Manipulating Programs with Full-Program Induction
We present a full-program induction technique for proving (a sub-class of) quantified as well as quantifier-free properties of programs manipulating arrays of parametric size N. Instead of inducting over individual loops, our technique inducts over the entire program (possibly containing multiple loops) directly via the program parameter N. Significantly, this does not require generation or use of loop-specific invariants. We have developed a prototype tool Vajra to assess the efficacy of our technique. We demonstrate the performance of Vajra vis-a-vis several state-of-the-art tools on a set of array manipulating benchmarks.
- 17 April 2020
- Published by Springer Nature
- Vol. 12078, 22-39
Open AccessVerifying Array Manipulating Programs with Full-Program Induction
We present a full-program induction technique for proving (a sub-class of) quantified as well as quantifier-free properties of programs manipulating arrays of parametric size N. Instead of inducting over individual loops, our technique inducts over the entire program (possibly containing multiple loops) directly via the program parameter N. Significantly, this does not require generation or use of loop-specific invariants. We have developed a prototype tool Vajra to assess the efficacy of our technique. We demonstrate the performance of Vajra vis-a-vis several state-of-the-art tools on a set of array manipulating benchmarks.