activity
20242026
collaborators

14 papers

cs.LG2026

Are Safety Guarantees in Neural Networks Safe? How to Compute Trustworthy Robustness Certifications

Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1

A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, re…

cs.AI2026

Towards Rigorous Explainability by Feature Attribution

Olivier Létoffé, Xuanxiang Huang, Joao Marques-Silva

For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such methods lack rigor and can mislea…

cs.LG2026

The Cost of Relaxation: Evaluating the Error in Convex Neural Network Verification

Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1

Many neural network (NN) verification systems represent the network's input-output relation as a constraint program. Sound and complete, representations involve integer constraints…

cs.AI2026

Interval Certifications for Multilayered Perceptrons via Lattice Traversal

Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris +1

In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustne…

cs.AI2025

Uncovering Bugs in Formal Explainers: A Case Study with PyXAI

Xuanxiang Huang, Yacine Izza, Alexey Ignatiev +1

Formal explainable artificial intelligence (XAI) offers unique theoretical guarantees of rigor when compared to other non-formal methods of explainability. However, little attentio…

cs.AI2025

Efficient & Correct Predictive Equivalence for Decision Trees

Joao Marques-Silva, Alexey Ignatiev

The Rashomon set of decision trees (DTs) finds importance uses. Recent work showed that DTs computing the same classification function, i.e. predictive equivalent DTs, can represen…