Searcharxiv⌕ Search

arXiv subjects

D. Richard Kuhn

Publications and source records attributed to D. Richard Kuhn.

7 recordsLinked to original sources
arXiv2026

DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

We introduce a gradient-free framework for identifying minimal, sufficient, and decision-preserving explanations in vision models by isolating the smallest subset of representational units whose joint activation preserves predictions. Unlike existing approaches that aggregate all units, often leading to cluttered saliency maps, our approach, DD-CAM, identifies a 1-minimal subset whose joint activation suffices to preserve the prediction (i.e., removing any unit from the subset alters the prediction). To efficiently isolate minimal sufficient subsets, we adapt delta debugging, a systematic reduction strategy from software debugging, and configure its search strategy based on unit interactions in the classifier head: testing individual units for models with non-interacting units and testing unit combinations for models in which unit interactions exist. We then generate minimal, prediction-preserving saliency maps that highlight only the most essential features. Our experimental evaluation demonstrates that our approach can produce more faithful explanations and achieve higher localization accuracy than the state-of-the-art CAM-based approaches.

cs.CV↗
arXiv2025

ABLE: Using Adversarial Pairs to Construct Local Models for Explaining Model Predictions

Machine learning models are increasingly used in critical applications but are mostly "black boxes" due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex models near a test instance using simple, interpretable models. However, these approaches often suffer from instability and poor local fidelity. In this paper, we propose a novel approach called Adversarially Bracketed Local Explanation (ABLE) to address these limitations. Our approach first generates a set of neighborhood points near the test instance, x_test, by adding bounded Gaussian noise. For each neighborhood point D, we apply an adversarial attack to generate an adversarial point A with minimal perturbation that results in a different label than D. A second adversarial attack is then performed on A to generate a point A' that has the same label as D (and thus different than A). The points A and A' form an adversarial pair that brackets the local decision boundary for x_test. We then train a linear model on these adversarial pairs to approximate the local decision boundary. Experimental results on six UCI benchmark datasets across three deep neural network architectures demonstrate that our approach achieves higher stability and fidelity than the state-of-the-art.

cs.LG↗
arXiv2019

Towards an Automated Unified Framework to Run Applications for Combinatorial Interaction Testing

Combinatorial interaction testing (CIT) is a well-known technique, but the industrial experience is needed to determine its effectiveness in different application domains. We present a case study introducing a unified framework for generating, executing and verifying CIT test suites, based on the open-source Avocado test framework. In addition, we present a new industrial case study to demonstrate the effectiveness of the framework. This evaluation showed that the new framework can generate, execute, and verify effective combinatorial interaction test suites for detecting configuration failures (invalid configurations) in a virtualization system.

cs.SE↗
arXiv2009

Role-Based Access Controls

While Mandatory Access Controls (MAC) are appropriate for multilevel secure military applications, Discretionary Access Controls (DAC) are often perceived as meeting the security processing needs of industry and civilian government. This paper argues that reliance on DAC as the principal method of access control is unfounded and inappropriate for many commercial and civilian government organizations. The paper describes a type of non-discretionary access control - role-based access control (RBAC) - that is more central to the secure processing needs of non-military systems than DAC.

cs.CR↗
arXiv2003

A Quantum Cryptographic Protocol with Detection of Compromised Server

This paper presents a hybrid cryptographic protocol, using quantum and classical resources, to generate a key for authentication and optionally for encryption in a network. One or more trusted servers distribute streams of entangled photons to individual resources that seek to communicate. An important class of cheating by a compromised server will be detected.

quant-ph↗
arXiv2003

Vulnerabilities in Quantum Key Distribution Protocols

Recently proposed quantum key distribution protocols are shown to be vulnerable to a classic man-in-the-middle attack using entangled pairs created by Eve. It appears that the attack could be applied to any protocol that relies on manipulation and return of entangled qubits to create a shared key. The protocols that are cryptanalyzed in this paper were proven secure with respect to some eavesdropping approaches, and results reported here do not invalidate these proofs. Rather, they suggest that quantum cryptographic protocols, like conventional protocols, may be vulnerable to methods of attack that were not envisaged by their designers.

quant-ph↗