58 citations · 96 across the 13 of their papers we have counts for
7 papers · 1 filter
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild +6
Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly conce…
Pitfalls of Explainable ML: An Industry Perspective
Sahil Verma, Aditya Lahiri, John P. Dickerson +1
As machine learning (ML) systems take a more prominent and central role in contributing to life-impacting decisions, ensuring their trustworthiness and accountability is of utmost…
Counterfactual Explanations for Machine Learning: Challenges Revisited
Sahil Verma, John Dickerson, Keegan Hines
Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form `…
Amortized Generation of Sequential Algorithmic Recourses for Black-box Models
Sahil Verma, Keegan Hines, John P. Dickerson
Explainable machine learning (ML) has gained traction in recent years due to the increasing adoption of ML-based systems in many sectors. Algorithmic Recourses (ARs) provide "what…
Removing biased data to improve fairness and accuracy
Sahil Verma, Michael Ernst, Rene Just
Machine learning systems are often trained using data collected from historical decisions. If past decisions were biased, then automated systems that learn from historical data wil…
ShapeFlow: Dynamic Shape Interpreter for TensorFlow
Sahil Verma, Zhendong Su
We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code. Sh…
Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review
Sahil Verma, Varich Boonsanong, Minh Hoang +3
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understa…