AIConfPaper
← Search

Berkant Turan

4 accepted papers

2026

Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings

Berkant Turan, Suhrab Asadulla, David Steinmann, Kristian Kersting, Wolfgang Stammer, Sebastian Pokutta
ICML 2026spotlight

While *Prover-Verifier Games* (PVGs) offer a promising path toward verifiability in nonlinear classification models, they have not yet been applied to complex inputs such as high-dimensional images. Conversely, expressive *concept encodings* effectively allow to translate such data into interpretabl…

Cited by 0Source ↗Scholar ↗
2025

Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation

Jan Pauls, Max Zimmer, Berkant Turan, Sassan Saatchi, Philippe CIAIS, Sebastian Pokutta +1
ICML 2025poster

With the rise in global greenhouse gas emissions, accurate large-scale tree canopy height maps are essential for understanding forest structure, estimating above-ground biomass, and monitoring ecological disruptions. To this end, we present a novel approach to generate large-scale, high-resolution c…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses

Grzegorz Gluch, Berkant Turan, Sai Ganesh Nagarajan, Sebastian Pokutta
NeurIPS 2025poster

We formalize and analyze the trade-off between backdoor-based watermarks and adversarial defenses, framing it as an interactive protocol between a verifier and a prover. While previous works have primarily focused on this trade-off, our analysis extends it by identifying transferable attacks as a th…

Cited by 0Source ↗Scholar ↗
2024

Interpretability Guarantees with Merlin-Arthur Classifiers

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta
AISTATS 2024poster

We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the classification decision. Our results are inspired…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗