arXiv AI September 28, 2026 By Kai Yao

Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance

The paper investigates whether pixels alone can determine an image’s origin—human, AI class, or specific generator—under adversarial edits. It establishes a minimax limit: the best possible robust acceptance gap equals the minimum total‑variation distance between the target distribution and attacked source distributions, independent of verifier design. The study also shows that practical public verifiers can fail before reaching this theoretical ceiling, highlighting the need to evaluate both statistical limits and deployed verifier behavior separately.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 28

A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection

arXiv:2607. 22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model.

By Ali Borji

safety

arXiv Computer Vision

Sep 10

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

arXiv:2609.10002v1 Announce Type: new Abstract: Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and t...

By Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira

multimodal safety

arXiv Machine Learning

Sep 16

The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks

arXiv:2606.22516v2 Announce Type: replace Abstract: Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assu...

By Yuhang Jiang, Xiaojing Chen

safety

arXiv Computer Vision

1d ago

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

arXiv:2605.25663v2 Announce Type: replace-cross Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the featur...

By Florent Tariolle, Florian Yger

safety

arXiv Machine Learning

Sep 22

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

The paper introduces RIBA, a reinforcement‑learning inspired black‑box adversarial attack that generates perturbations for neural networks with fewer queries than existing methods. RIBA achieves a 25.4% reduction in median queries on ResNet‑18/Cifar10 and a 22.5% reduction on Vit‑B/16/ImageNet, while matching white‑box attack performance on an adversarially trained model.

By Florian Krone, Elena Hoemann, Sven Hallerbach

llms computer-vision reinforcement-learning safety

arXiv AI

Aug 18

Fast Test-Time Refinement for Robust Learned Image Compression

arXiv:2608. 15113v1 Announce Type: cross Abstract: Learned image compression (LIC) has demonstrated remarkable rate-distortion (RD) performance in benign settings.

By Jiaming Liang, Chi-Man Pun, Weisi Lin

safety

One email a morning, machine-written

Related stories

A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

Fast Test-Time Refinement for Robust Learned Image Compression