Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection
Detecting AI generated images is a challenging yet essential task. A primary difficulty arises from the detectors tendency to rely on spurious patterns, such as compression artifacts, which can influence its decisions. These issues often stem from specific patterns that the detector associates with the real data distribution, making it difficult to isolate the actual generative traces. We argue that an image should be classified as fake if and only if it contains artifacts introduced by the generative model. Based on this premise, we propose Stay Positive, an algorithm designed to constrain the detectors focus to generative artifacts while disregarding those associated with real data. Experimental results demonstrate that detectors trained with Stay Positive exhibit reduced susceptibility to spurious correlations, leading to improved generalization and robustness to post processing. Additionally, unlike detectors that associate artifacts with real images, those that focus purely on fake artifacts are better at detecting inpainted real images.
Code (1)
Tasks
Fake Image DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model
Objective: Molecular testing (MT) classifies cytologically indeterminate thyroid nodules as benign or malignant with high sensitivity but low positive predictive value (PPV), only using molecular profiles, ignoring ultra…
Multimodal Deep LearningMultiple Instance LearningSensitivityScalable Event-Based Video Streaming for Machines with MoQ
Lossy compression and rate-adaptive streaming are a mainstay in traditional video steams. However, a new class of neuromorphic ``event'' sensors records video with asynchronous pixel samples rather than image frames. The…
Toward a standardized methodology for constructing quantum computing use cases
We propose a standardized methodology for developing and evaluating use cases for quantum computers and quantum inspired methods. This methodology consists of a standardized set of questions which should be asked to dete…
Probe Choice Changes Canary-Memorization Verdicts: Three Post-Hoc Disagreement Case Studies in a Text-Dominant LoRA-Tuned Autoregressive Testbed
We audit a fixed prefix-window mean-NLL memorization probe (K=20) on a Qwen2.5-VL-7B canary testbed and report three post-hoc cases where it disagrees with full-span secret NLL or greedy exact-recall. C3 (false negative,…
Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!
We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario. Our work builds upon the iWildCam dataset, and, to the best of our knowledge, we are the first to…
Anomaly DetectionUnsupervised Anomaly Detection