The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? Existing methods have grown as elaborate as the genera...
arXiv:2505. 03201v4 Announce Type: replace-cross Abstract: Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential.
The paper introduces a Focal Log-Frequency Loss (f-loss) to counteract the spectral imbalance in pixel-space flow matching, where low frequencies dominate training. By balancing learning signals across frequencies and combining early frequency-domain supervision with later pixel-space refinement, the method accelerates convergence by up to 40% and improves FID and perceptual fidelity across multiple model scales. It requires no architectural changes and can replace existing flow matching losses as a drop‑in solution.
The paper introduces a multi‑view, confusion‑guided ensemble framework for synthetic image attribution, combining FFT‑ConvNeXt, DINOv2, CLIP, and Xception to capture frequency, semantic, and forensic cues. Extensive data augmentation simulates realistic post‑processing, while a binary expert classifier and class‑adaptive confidence calibration address ambiguities between similar diffusion models. The approach achieved 99.53% on the public leaderboard and 99.20% on the private leaderboard for the ICANN 2026 DLMMDD Workshop challenge.
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...
arXiv:2606. 28226v1 Announce Type: cross Abstract: Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference.
arXiv:2511.11286v4 Announce Type: replace-cross Abstract: Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenario...
arXiv:2606. 10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output.
The paper demonstrates that a targeted adversarial perturbation can reduce a vision‑language model’s training loss to near zero for a fixed target caption, yet the same model, when generating freely, still produces the correct description. This phenomenon, termed the train/inference gap, is traced to a single autoregressive step where the target token’s rank is fixed across all images, and further analysis shows that the language decoder, rather than the visual encoder, determines whether the corrupted signal is amplified or suppressed. The study uses a controlled two‑stage PGD attack on Qwen2.5‑VL‑7B‑Instruct and evaluates the effect on 200 held‑out COCO images, revealing that adversarial robustness in autoregressive VLMs largely depends on the language decoder’s prior. whyItMatters":"The findings suggest that defenses and faithfulness evaluations for deployed vision‑language models should focus on the language decoder rather than the visual encoder, as the former is the key determinant of robustness to adversarial perturbations."
SpectralCanary introduces a simple method for auditing whether a text‑to‑image model has been fine‑tuned on a specific image collection. It embeds a low‑frequency visual signal by blending a fixed canary image into every dataset image with a smooth low‑pass mask, leaving captions unchanged and avoiding per‑image optimization. A lightweight verifier then detects this signal in a model’s generated outputs, achieving high true‑positive rates across multiple datasets and architectures while preserving image quality.
arXiv:2604.05819v2 Announce Type: replace-cross Abstract: Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical...
The paper investigates how knowledge distillation from event cameras to RGB images can alter the inductive biases of convolutional neural networks. By transferring learning from the event domain, the authors find that models gain color invariance, a shape bias, and improved robustness to high‑frequency noise, largely due to reduced reliance on texture and increased emphasis on edge‑based object shape. These changes are evidenced by early‑layer processing differences and a spectral trade‑off between robustness to missing high‑frequency content and vulnerability to its contamination or geometric disruption.