The impressive visual quality and ubiquity of AI-generated images call for reliable and robust detection methods. Reconstruction-based detectors have emerged as a promising direction for transparent and training-free identification of synthetic images.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
By Nicolas Stalder, Benjamin F. Grewe, Matteo Saponati, Pau Vilimelis Aceituno
arXiv:2607. 04145v1 Announce Type: new Abstract: Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models.
By Naman Goyal, Milan Chaudhari
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
By Wenjing Lu, Zerui Tao, Yuning Qiu, Dongping Zhang, Yang Yang, Qibin Zhao
The paper introduces a general empirical worst‑case framework for testing outlier‑detection methods in subjective image quality assessment. It presents adversarial attack generators that optimize ratings to maximize the discrepancy between mean opinion scores (MOS) and ground truth, applying these to both discrete and continuous rating scales. The study evaluates several hard and soft outlier‑detection techniques, revealing significant differences in worst‑case performance and proposes low‑complexity methods that achieve strong empirical results.
By Dietmar Saupe
arXiv:2603. 22590v2 Announce Type: replace Abstract: With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become highly relevant.
By Mat\'ias Pizarro, Raghavan Narasimhan, Jonas Killian, Asja Fischer