AIConfPaper
← Search

Valentyn Boreiko

6 accepted papers

2026

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods

Michal Moshkovitz, Suraj Srinivas, Lesia Semenova, Nave Frost, Cyrus Rashtchian, Valentyn Boreiko +4
ICML 2026poster

Despite the proliferation of Explainable AI (XAI) techniques—from feature attributions to sparse autoencoders—explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action. This gap reflects foundational shortcomings: resear…

Cited by 0Source ↗Scholar ↗
2025

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek, Matthias Hein, Jonas Geiping
ICML 2025poster

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in fluency and computational effort. In this work, we propose a unifi…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

How Much Can We Forget about Data Contamination?

Sebastian Bordt, Suraj Srinivas, Valentyn Boreiko, Ulrike von Luxburg
ICML 2025poster

The leakage of benchmark data into the training data has emerged as a significant challenge for evaluating the capabilities of large language models (LLMs). In this work, we challenge the common assumption that small-scale contamination renders benchmark evaluations invalid. First, we experimentally…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Identification of Systematic Errors of Image Classifiers on Rare Subgroups

Jan Hendrik Metzen, Robin Hutmacher, N. Grace Hua, Valentyn Boreiko, Dan Zhang
ICCV 2023poster

Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data. These systematic errors can impact both fairness for demographic minority groups as w…

Cited by 22PDF ↗Scholar ↗
2023

Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet

Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein
ICCV 2023poster

Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up spurious features in the training data, its predictions can fail in unexpected ways. In this paper, we develop a framewor…

Cited by 30PDF ↗code ↗Scholar ↗
2022

Diffusion Visual Counterfactual Explanations

Maximilian Augustin, Valentyn Boreiko, Francesco Croce, Matthias Hein
NeurIPS 2022accept

Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are “small” but “realistic” semantic changes of the image changing the classifier decision. Current approaches for the generation of VCEs are restricted to adversarially robust mo…

Cited by 81Source ↗PDF ↗code ↗Scholar ↗