arXiv Machine Learning September 3, 2026 By Dietmar Saupe

Adversarial Stress Testing of Outlier Detection in Subjective Image Quality Assessment

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

safety

arXiv Computer Vision

Oct 8

VCR-Bench: A Modular Open-Source Benchmark for Video Classification Robustness

arXiv:2610.08936v1 Announce Type: new Abstract: Robustness of image classification has several benchmarks, but their video counterparts are absent. In video classification temporal dimension introduc...

By Maksim Plinskiy, Aleksandr Gushchin, Sergey Lavrushkin, Dmitriy S. Vatolin, Anastasia Antsiferova

computer-vision benchmarks safety

arXiv AI

Sep 3

Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework

The paper introduces a new task called Quality Anomaly Perception for UGC Image Enhancement (UEAP) and presents the first benchmark dataset, UEAP-4k, featuring fine‑grained annotations of anomaly categories, locations, and severity levels in real‑world user‑generated content. It proposes the Difference‑Fusion Anomaly Perception Method (DFAP‑UGC), which fuses explicit differences between enhanced images and their references using dense spatial querying, regional verification, and quality‑aware ranking to robustly identify localized anomalies. A Locality‑Aware Dynamic Task Prioritization (LADTP) training strategy is also introduced to enable efficient end‑to‑end learning without multi‑stage overhead, and experiments demonstrate that DFAP‑UGC outperforms adapted classical baselines.

By Yan Zhong, Gefei Chen, Qiufang Ma, Zhen Wang, Zhiwei Fan, Lei Shi, Tingting Jiang

benchmarks

arXiv Computer Vision

Sep 10

A VLM Answer Is Not an Anomaly Score: Rank Compression Across Image and Video Anomaly Detection

arXiv:2608.21244v2 Announce Type: replace Abstract: Anomaly detection aims to identify observations that deviate from normal patterns. Recent work uses pretrained vision-language models (VLMs) for tr...

By Inpyo Song, Jangwon Lee

llms multimodal benchmarks

arXiv Machine Learning

Jul 7

Binary Iterative Method for Non-targeted Adversarial Attack

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

safety

Hugging Face Trending Papers

Aug 17

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 AI

Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

llms rag diffusion multimodal safety