The paper introduces ICON Decomposition, a method for auditing deep neural networks by decomposing layer-wise representations into independent concept contributions. Unlike existing techniques that rely on linear probes or concept activation vectors, ICON quantifies the variance share each concept explains while conditioning on all other concepts and the outcome, allowing comparison across layers and concept types. Experiments on simulated data, skin‑cancer, and neuroimaging models show that ICON more accurately recovers true concept importance and can distinguish learned shortcuts from correlated concepts, as validated by retraining and out‑of‑distribution tests.
arXiv:2608.26083v2 Announce Type: replace-cross Abstract: Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Auditing for shortcuts requires testing many...
ICON Decomposition is a new method for explaining deep neural networks by quantifying how much variance each concept explains in a network layer after accounting for all other concepts and the outcome. Unlike previous concept‑based methods that evaluate concepts in isolation, ICON can distinguish genuine model reliance from spurious correlations. Experiments on synthetic data, skin‑lesion, and brain‑imaging models show that ICON recovers concept importance more accurately, isolates truly relied‑upon concepts, and provides sparse explanations validated through retraining and out‑of‑distribution testing.
arXiv:2606. 01843v1 Announce Type: cross Abstract: Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen manipulations.
arXiv:2510. 15770v4 Announce Type: replace-cross Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control.
arXiv:2607. 25117v1 Announce Type: cross Abstract: Deep learning models for ECG image classification may achieve high accuracy by exploiting non-physiological visual cues instead of ECG waveform morphology.
arXiv:2311. 02960v5 Announce Type: replace Abstract: Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data.
arXiv:2607. 04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model.
arXiv:2606. 16535v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols.
arXiv:2608. 05424v1 Announce Type: cross Abstract: Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals.
arXiv:2606. 19882v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts.
arXiv:2602.01718v2 Announce Type: replace Abstract: Predicting generalization from quantities available before target-test evaluation remains a central challenge in deep learning. The systematic benc...
arXiv:2509. 04009v2 Announce Type: replace-cross Abstract: Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or unintended but statistically relevant signals.