ForensicConcept: Transferable Forensic Concepts for AIGI Detection

• URL: http://arxiv.org/abs/2606.07034v1
• Date: Fri, 05 Jun 2026 08:25:34 GMT
• Title: ForensicConcept: Transferable Forensic Concepts for AIGI Detection
• Abstract summary: We propose ForensicConcept, a framework that extracts explicit forensic concepts from detectors and enables their transfer across backbones.<n>Our method localizes decision-critical patches via Transformer attribution, clusters them into a compact concept codebook, and uses a concept-aligned projection to produce auditable evidence readouts.
• Score: 81.29606528968698
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI-generated image detectors achieve high accuracy on in-distribution data but often fail on unseen generators. A key obstacle to understanding this failure is the black-box nature of current detectors: they do not reveal which evidence drives their decisions. We propose ForensicConcept, a framework that extracts explicit forensic concepts from detectors and enables their transfer across backbones. Our method localizes decision-critical patches via Transformer attribution, clusters them into a compact concept codebook, and uses a concept-aligned projection to produce auditable evidence readouts. Motivated by prior studies showing that DINO representations can guide diffusion generation and exhibit concept-level correspondence with diffusion features, we introduce a generation-trace reference based on CleanDIFT diffusion features and quantify backbone-trace alignment via neighborhood-structure consistency (CKNNA). We further propose concept codebook injection to transfer diffusion-derived concepts into target backbones. Experiments on GenImage, GAN-family, and Chameleon benchmarks show consistent improvements over prior methods. We also find that CKNNA alignment predicts transfer effectiveness, providing a principled explanation for why some backbones yield more transferable forensic evidence than others.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation [23.254574194880234]
  Fake news increasingly relies on cross-modal image-text forgeries.<n>Existing methods produce black-box detection results without any decision rationale.<n>We propose a multi-modal manipulation detector based on an Evidence-Grounded Forensic Reasoning framework.
  arXiv  Detail & Related papers  (2026-08-08T08:41:26Z)
• TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors [76.4118981404995]
  Trajectory-Injected Generative Attack (TIGA) is a source-image-free and training free framework that generates detector-evasive images.<n>TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation.<n>TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations.
  arXiv  Detail & Related papers  (2026-07-28T15:51:39Z)
• ForensicsTok: Forensics-Guided Tokenized Modeling for Image Tampering Localization [31.83661814822312]
  We propose ForensicsTok, which reformulates image manipulation localization as an autoregressive sequence generation task.<n>ForensicsTok directly generates spatially grounded token sequences, enabling precise mask prediction without intermediary supervision.
  arXiv  Detail & Related papers  (2026-06-23T13:06:18Z)
• Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection [50.08054676999716]
  We present Probabilistic Concept Graph Reasoning (PCGR), an interpretable and evolvable framework that reframes multimodal misinformation detection as structured and concept-based reasoning.<n>PCGR achieves state-of-the-art MMD accuracy and robustness to emerging manipulation types, outperforming prior methods in both coarse detection and fine-grained manipulation recognition.
  arXiv  Detail & Related papers  (2026-03-26T09:08:31Z)
• REVEAL: Reasoning-enhanced Forensic Evidence Analysis for Explainable AI-generated Image Detection [30.963994372913092]
  We introduce textbfREVEAL-Bench, the first reasoning-enhanced multimodal benchmark for AI-generated image detection.<n>Our framework integrates detection with a novel expert-grounded reinforcement learning.<n> REVEAL significantly enhances detection accuracy, explanation fidelity, and robust cross-model generalization.
  arXiv  Detail & Related papers  (2025-11-28T13:11:08Z)
• On Thin Ice: Towards Explainable Conservation Monitoring via Attribution and Perturbations [3.4574594310498266]
  We train a Faster R-CNN to detect harbor seals using aerial imagery from Glacier Bay National Park.<n>We assess explanations along three axes relevant to field use.<n>We translate these findings into actionable next steps for model development.
  arXiv  Detail & Related papers  (2025-10-24T17:46:24Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution [20.93589028730206]
  We introduce emphconcept-level attribution via a novel method called emphConcept-TRAK.<n> Concept-TRAK extends influence functions with two key innovations: (1) a reformulated diffusion training loss based on diffusion posterior sampling, enabling robust, sample-specific attribution; and (2) a concept-aware reward function that emphasizes semantic relevance.
  arXiv  Detail & Related papers  (2025-07-09T05:03:57Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)
• Closed-Form Factorization of Latent Semantics in GANs [65.42778970898534]
  A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images. In this work, we examine the internal representation learned by GANs to reveal the underlying variation factors in an unsupervised manner. We propose a closed-form factorization algorithm for latent semantic discovery by directly decomposing the pre-trained weights.
  arXiv  Detail & Related papers  (2020-07-13T18:05:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.