collaborators

5 papers

cs.LG2026

WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents

Zhixiang Guo, Siyuan Liang, Shi Fu +4

Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated automated evaluation methods. A k…

cs.CV2026

ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP

Linxiang Su, András Balogh

Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively…

cs.LG2026

When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models

Zhixiang Guo, Siyuan Liang, Andras Balogh +4

Generative world models (WMs) are increasingly used to synthesize controllable, sensor-conditioned driving videos, yet their reliance on physical priors exposes novel attack surfac…

cs.LG2026

Verification of the Implicit World Model in a Generative Model via Adversarial Sequences

András Balogh, Márk Jelasity

Generative sequence models are typically trained on sample sequences from natural or formal languages. It is a crucial question whether -- or to what extent -- sample-based trainin…

cs.LG2024

How not to Stitch Representations to Measure Similarity: Task Loss Matching versus Direct Matching

András Balogh, Márk Jelasity

Measuring the similarity of the internal representations of deep neural networks is an important and challenging problem. Model stitching has been proposed as a possible approach,…