arXiv:2606. 25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud.
The paper reviews one‑pixel attacks (OPAs), highlighting their extreme adversarial fragility across domains such as medical diagnosis, autonomous driving, biometrics, and quantum communication. It presents a PRISMA‑guided synthesis of studies from 2017 to 2026, offering a unified taxonomy that covers algorithmic foundations, black‑box evolutionary optimization, hybrid and program‑synthesis attacks, defence mechanisms, interpretability tools, and domain‑specific vulnerabilities. The review identifies dominant Differential Evolution strategies, emerging efficiency‑optimized and saliency‑guided methods, and gaps in dataset diversity, transferability, and evaluation standards, while proposing future research directions and a regulatory framework for robustness testing and AI security governance.
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.
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
arXiv:2609.26384v1 Announce Type: new Abstract: Medical image interpretation is high-volume and time-consuming, and while AI interpretation can reduce workload, fully autonomous deployment carries po...
The paper introduces a new framework for generating medical image counterfactuals that does not rely on auxiliary generative models. By extracting causal evidence directly from a classifier, the method deterministically produces edits within user-specified regions, requiring no additional training. Experiments on real-world medical imaging datasets show that these counterfactuals alter classifier predictions while staying closer to the original image than generative baselines, offering a clearer view of the model’s decision boundary.
arXiv:2607. 02596v1 Announce Type: cross Abstract: Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.
arXiv:2601. 14300v4 Announce Type: replace Abstract: Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models.
arXiv:2610.03142v1 Announce Type: new Abstract: Deep neural networks remain vulnerable to adversarial perturbations, which can distort not only predictions but also confidence scores, undermining unc...
arXiv:2608.24281v1 Announce Type: new Abstract: Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object de...
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically consider images in isolation.
arXiv:2609.14290v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in healthcare imaging pipelines for diagnostic support, and training-time attacks against them are...