arXiv AI August 14, 2026 By Yicheng Bao, Xiahui Guo, Xuhong Wang, Xin Tan

SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data

arXiv:2608. 12876v1 Announce Type: cross Abstract: Detecting AI-generated images is only half the task: a deployed detector must also justify its verdict, yet existing detectors inherit three failure modes from their training data: real and fake images collected from different sources invite provenance shortcuts, supervised explanation corpora teach templated rationales, and a static forgery corpus leaves the decision boundary standing still while generators keep moving.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 26

Adversarial Robustness of AI-Generated Image Detectors in the Real World

arXiv:2410. 01574v4 Announce Type: replace-cross Abstract: The rapid advancement of Generative Artificial Intelligence (GenAI) capabilities is accompanied by a concerning rise in its misuse.

By Sina Mavali, Jonas Ricker, David Pape, Asja Fischer, Lea Sch\"onherr

benchmarks safety

arXiv AI

Jun 6

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

arXiv:2503. 01734v3 Announce Type: replace-cross Abstract: Attacks on machine learning models have been extensively studied through stateless optimization.

By Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley, Eric Pauley, Josiah Hanna, Patrick McDaniel

agents computer-vision reinforcement-learning benchmarks safety

arXiv AI

Aug 7

DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning

arXiv:2511. 04949v2 Announce Type: replace-cross Abstract: Rapid advances in generative AI have led to increasingly realistic deepfakes, posing growing challenges for law enforcement and public trust.

By Tharindu Fernando, Clinton Fookes, Sridha Sridharan

agents diffusion reinforcement-learning robotics benchmarks safety

Hugging Face Trending Papers

2d ago

Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples

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.

benchmarks safety

arXiv Machine Learning

Jun 18

RUB: Evaluating Residual Knowledge in Unlearned Models

arXiv:2504. 14798v2 Announce Type: replace Abstract: Machine Unlearning (MUL) has emerged as a key mechanism for privacy protection and content regulation, yet current techniques often fail to guarantee the complete removal of sensitive information.

By Hao Xuan, Xingyu Li

diffusion benchmarks safety

arXiv AI

Jun 11

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

arXiv:2606. 12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations.

By Xinhai Zou, Chang Zhao, Alireza Aghabagherloo, Dave Singel\'ee, Robin Degraeve, Bart Preneel

reinforcement-learning safety

Related stories

Adversarial Robustness of AI-Generated Image Detectors in the Real World

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning

Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples

RUB: Evaluating Residual Knowledge in Unlearned Models

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization