Papers for
digital forensics analysts
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
FIBER improves detection of AI-generated text across domains
FIBER: Bayesian Fusion of Fast-DetectGPT and IRT-Informed Detector Evidence for LLM-Generated Text Detection
Abstract: Detecting large language model (LLM)-generated text remains challenging under domain and generator shifts. Supervised detectors may generalize poorly, while zero-shot methods often rely on individual statistical signals without leveraging historical detector behavior. We propose FIBER (Fast-DetectGPT with IRT-informed Bayesian Evidence Recalibration), which integrates continuous Fast-DetectGPT scores with auxiliary detector outputs through Bayesian evidence fusion. Item response theory (IRT) models historical detector-correctness patterns, providing class-conditional detector-output likelihoods through marginalization over latent text representations. These likelihoods are combined with Fast-DetectGPT score densities and a historical class prior for prediction. When historical Fast-DetectGPT scores are unavailable, a variant called FIBER-Stream estimates class-specific score distributions from an unlabeled batch. On a 32,000-text multi-domain benchmark, FIBER achieves the highest accuracy (0.620) and improves mean AUC over Fast-DetectGPT (0.664 versus 0.600) under five-fold cross-validation. FIBER also consistently improves AUC across four individual domains. Under out-of-distribution transfer, FIBER-Stream achieved an AUC of 0.911, compared with 0.889 for FIBER and 0.922 for Fast-DetectGPT alone. These results demonstrate the potential of integrating complementary detector evidence and historical information to improve detection performance across heterogeneous settings.
Explainable deepfake detection improves with metric-aligned optimization
Metric-Aligned Group Relative Policy Optimization for Explainable Deepfake Detection
Abstract: Deepfake detectors are commonly evaluated on real/fake classification alone, but real-world applications require explanations of the visual evidence behind each prediction. Joint vision-language models struggle with authenticity assessment, producing "real" narratives for manipulated images. To address this, we propose a decoupled predict-then-explain pipeline as our submission to the ACM Multimedia 2026 Explainable Deepfake Detection Challenge, with methods trained and evaluated on the XPlainVerse benchmark. A vision-foundation-model ensemble first classifies the image, then a Qwen3-VL-8B model generates a decision-conditioned explanation of the visual evidence. For fake images, a second Qwen3-VL-8B compresses that text into a short non-expert summary without using the image. We further apply metric-aligned Group Relative Policy Optimization (GRPO) to optimize both explainers against the challenge criteria. Under matched conditions, GRPO raises complex BERTScore-F1 from 0.686 to 0.712 and also improves grounding (entity and evidence F1); our submission ranked first on complex BERTScore-F1 and seventh overall.
Image source attribution for fine-tuned stable diffusion models
Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline
Abstract: Designing systems that attribute a generated image to its source model has lately become a major area of AI research. Most existing datasets and systems related to image source attribution are targeted towards the detection of architectural signatures of the source models. Distinct from this, focusing on stable diffusion, we introduce a novel task, IntrAA-SD, Intra-Architecture source Attribution for Stable Diffusion, where the source models to be differentiated share the same architectural backbone and differ only due to fine-tuning. The proposed task aligns with the emergence of fine-tuned generators having the same architecture, like Juggernaut XL and RealVis XL, which are fine-tuned versions of Stable Diffusion XL (SDXL). We provide a first-of-its-kind $140$K-image benchmark dataset containing images generated from different fine-tunes of SDXL, along with in-domain and out-of-distribution prompts. We also provide a baseline framework for IntrAA-SD, which leverages a style-conditioned Mixture-of-Experts network. It uses a frozen CLIP backbone to capture the image style and gate the MoE, which processes fine-tuned trace features from a high-resolution LoRA-adapted DINOv2 network. The fine-tuned models used, the prompting strategies considered, and the formation details employed in the novel dataset are elaborated. Our baseline intra-architecture source attribution method is evaluated in terms of attribution accuracy on our dataset, and ablation studies are also performed. Code and dataset is available at https://github.com/mallikagarg/IntrAA-SD.
New method improves efficiency of locating AI-generated text watermarks
Query-efficient scan-and-search watermark localization
Abstract: Recently, the detection of AI-generated content has been of particular importance in various fields of our society. For accountability purposes, many large language models (LLMs) have implicitly watermarked their outputs. Localizing such watermarks requires a piece of text to undergo an additional verification process. Existing localization methods typically rely on dense token-level scoring, making verification costly even when an LLM-generated watermark only sparsely appears. To tackle this problem, we design a new adaptive allocation strategy that first maintains broad document coverage and then progressively concentrates the detection budget on regions that exhibit stronger watermark evidence or are more likely to contain watermarked content. We then transform the statistical signals from the selected regions into e-values and employ the proposed token-weighted e-BH procedure to determine the localized watermark regions. The resulting framework is called BELL (Budgeted E-evidence Localization for LLM Watermarks). Theoretically, BELL can control the token-weighted false discovery rate (FDR) without independence assumptions across regions. Finally, extensive experimental results demonstrate that BELL consistently outperforms competing methods across multiple LLMs, datasets, and watermarking schemes.
Deep networks find fake images different from real even under abstraction
The Search for Statistical Indistinguishability Between Real and Fake Images
Abstract: Images produced by generative models appear strikingly similar to real ones. In this work, we study whether perfection has been reached by generated content in terms of matching the properties of real data. We train deep neural networks to separate real data from fake and observe their test accuracies. Only a chance performance has any scope of proving statistical indistinguishability. However, since generative models are known to sometimes introduce small errors, e.g., low level checkerboard artifacts, we create progressive abstractions of the original real/fake images to potentially bring them to a space where those artifacts get wiped away. These include operations such as blurring, downsizing, cropping, converting RGB images into edge/semantic maps, etc. To our surprise, almost none of the abstractions are able to make fake data indistinguishable from real. The only cases when neural network based classifiers fail to separate the two categories is when the data is abstracted to such an extent that the original content seems mostly lost to the human eye, e.g., downsizing a $256 \times 256$ RGB image of human face to $4 \times 4$ resolution. We observe this trend across four different datasets of varying complexity (MNIST, CelebA, FFHQ and GenImage) and across various types of generative models (GANs, VAEs, diffusion models). This shows that the nature of fake artifacts extends all the way from low level to very high level in images. The simple implication is that fake images are much more different from real than we are used to think.
Large language models improve detection of multiple authors writing styles
Multi-author style detection with stylistic embeddings
Abstract: We investigate the use of Large Language Models (LLMs) in multi-author style change detection. Using off-the-shelf LLMs or supervised fine-tuning solely within the target domain fails to yield effective features; for this reason, we propose cross-domain transfer learning with LLM-based embeddings fine-tuned for authorship verification. We fine-tune Mistral-7B embedding model and compare it with DeBERTa, used in the state-of-the-art (SOTA) systems in PAN-25 multi-author writing style analysis challenge. Results show that DeBERTa and Mistral excel in different user-generated text scenarios. We exploit this diversity by combining both embeddings, leading to more effective style change detection.
Improved method detects mixed watermarks in AI-generated text accurately
Token-Level Attribution of Multi-Mode LLM Watermarks: Optimal Rule and Belief Weighting
Abstract: A watermark verifier may hold many modes, i.e., secret keys, and a document may mix spans of different modes with unwatermarked text. Directly reporting the mode with the largest pivotal statistic (pivot) inflates the Type I error, and restoring the nominal level reduces power as candidate modes are added. We formulate token-level multi-mode attribution for the Gumbel-max watermark as maximizing correct-label power under a Type I error constraint given a mode prior. We show that the optimal rule reports the mode with the largest prior-weighted alternative density and rejects when this density exceeds one common threshold. Based on this rule, we propose the Belief-weighted Likelihood Attribution with Density Estimation (BLADE) detector. It estimates the mode prior from neighboring pivots and the alternative density from reference token probabilities. Under a conditional product model of the pivots, it keeps the exact Type I error. We further show that BLADE approaches the optimal rule as its prior and density estimates improve, with a sharp coefficient on the density error. On OPT-1.3B and other open-weight large language models, BLADE attains higher correct-label power than the compared detectors across candidate counts, token-substitution rates, generation temperatures and generator models.
Human accuracy varies by deepfake model and improves with targeted training
From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images
Abstract: Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical research on human performance in detecting deepfake face images has not kept pace. It remains unclear if (and how) detection performance varies across generative models and whether model-specific training improves detection more effectively than general-purpose training. In this paper, we propose the \emph{Deepfake Face Artifact Taxonomy} (DFAT), a cross-model taxonomy of human-recognizable visual artifacts in deepfake face images, based on which we build both general-purpose and model-specific training materials. Through an online experiment ($n = 524$), we examined human performance in detecting deepfake face images and evaluated training efficacy across five representative generative models: three GAN-based, one diffusion-based, and one MLLM (GPT-5). Our results show that participants' detection accuracy was strongly model-dependent and that images generated by more recent and advanced models were not necessarily harder to detect. After training, participants achieved significant performance gains across most conditions, and their improvement varied by model. Notably, model-specific training generally yielded greater numerical gains than general-purpose training. In a five-month follow-up test ($n = 342$), we observed no significant decline in detection accuracy and no significant increase in perceived stress. Overall, our findings provide actionable insights for designing effective, sustainable, and targeted training programs to counter the growing threat posed by deepfakes.
GROB multi-agent system investigates public internet traces for agent activity
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
Abstract: We present GROB, a multi-agent architecture for investigating candidate autonomous-agent activity through public Internet traces when privileged telemetry is unavailable. The system performs controlled, read-only collection of public traces and preserves selected observations for later resolution. In a frozen September 2026 corpus, several collected traces became more informative as additional public evidence emerged. The strongest result concerns Census-labelled identifiers captured on 9 September. Public revision records later resolved these identifiers to specific Census requests from 16 - 17 June. Other results show weaker links between traces collected by GROB and evidence reconstructed or reported later. These links vary in strength, and only some can be tied to specific public records. The results show that sparse public traces can remain useful even before their significance is fully understood. Such evidence can support later reconstruction, but public traces alone do not establish organizational attribution. Execution identity presents a separate problem, as continuity of agent identity remains an active research question for autonomous language-model agents.
LLMs detect AI-generated text with varying success across versions
Using LLMs to Detect LLM-Generated Texts: A Cross-Generation Analysis
Abstract: Automated detection of LLM-generated texts (LGTs) is critical, yet dedicated detectors often struggle to generalize across domains and models. While general-purpose LLMs offer flexible zero-shot authorship classification with explanatory rationale, their detection behavior, especially regarding self-detection versus cross-detection across model generations, remains poorly understood. We systematically evaluate 15 LLMs spanning three model generations as both generators and detectors. Using a benchmark of 1,000 human-written texts and 15,000 LGTs (1,000 per model), we collected over 233,000 binary classifications alongside natural-language explanations. Our results reveal that detection efficacy is primarily driven by detector capability rather than generator provenance, although outputs from newer generators remain notably harder to detect. Crucially, statistical comparisons show no systematic advantage or disadvantage for self-detection across models. Error analysis further exposes generational bias shifts: first-generation detectors under-detect LGTs (high false-negative rates), second-generation detectors over-flag human texts (high false-positive rates), and the latest models achieve balanced trade-offs. Finally, we highlight significant inconsistencies in how different LLMs apply textual cues to justify their decisions. Code: https://github.com/hyyuan/detect-llm-generated-texts.
Semv framework improves multimedia verification with self evolving memory
Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences
Abstract: Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.
Agentic ai improves open world fake image detection by better evidence handling
Dissecting Agentic Forensics: The Role of Triage, Prompting, and Evidence Arbitration in Open-World Fake Image Detection
Abstract: Image forensics is increasingly an open-world problem: manipulations range from fully synthetic images to localized edits, splicing and swapping, while most forensic detectors remain specialized to a single manipulation family. Agentic AI has recently emerged as a promising solution. In principle, such systems can assess the reliability of individual detectors, identify out-of-scope evidence, and arbitrate conflicting reports. However, it remains unclear which components actually drive performance and whether their benefits persist under distribution shift. To answer these questions, we study a training-free agentic framework built around specialist detectors, per-detector triage, and conflict-aware evidence arbitration. Using six configurations and three multimodal large language model backbones, we dissect the role of triage, prompting, and reasoning quality on both in-distribution and out-of-distribution data. Our results show that naive detector fusion suffers from severe false-positive rates on authentic images. Triage and prompting consistently improve performance by filtering unreliable evidence and exposing detector limitations. However, the dominant factor is represented by reasoning itself: A stronger judge substantially outperforms a weaker one, particularly under distribution shift. Most notably, manipulation recall is nearly saturated across all configurations, indicating that the main challenge of open-world image forensics is not detecting manipulations, but calibrating trust in specialized forensic tools and arbitrating conflicting evidence.
Instruction based multi face forgery detector improves detection accuracy
IMFD: End-to-end Multi-Face Forgery Detection through Instruction-based Large Vision-Language Models
Abstract: The rapid increase of deepfakes has raised significant concerns due to their spread on social media. Traditional multi-face forgery detectors crop and verify each face independently, ignoring background context and inter-face relationships, which often yields suboptimal performance. To overcome these limitations, we leverage instruction-based Large Vision-Language Models (LVLMs), which can interpret entire images and follow complex textual instructions. We propose a simple yet effective single-stage multi-face forgery detector, called IMFD (Instruction-based Multi-face Forgery Detector), which is trained end-to-end to jointly localize faces and predict per-face forgery labels. Rather than treating face box prediction only as a joint objective, IMFD explicitly integrates predicted face bounding boxes into the instruction as visual cues that enhance instruction grounding and forgery detection. To support the training and evaluation of IMFD, we convert existing multi-face forgery datasets into an instruction-based format. Experimental results and analyses show that IMFD improves multi-face forgery detection by integrating face bounding boxes into the instruction, and consistently outperforms various state-of-the-art methods.
ChatGPT images dataset reveals challenges in detecting image generator versions
ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation
Abstract: An image tool can change its underlying generator while retaining its public name, making version attribution from online posts ambiguous. We study this problem after the ChatGPT Images 2.5 launch. Our frozen collection contains 3,478 images from 2,440 posts across 8 sources. Recorded posting times fall within the first 51.1 hours after the announcement. It records three attribution tiers and retains standalone images after image-form filtering and targeted review. Caption claims and host records provide admission evidence, not independently verified generator identity. The observed content profile depends on the source mixture: NightCafe supplies 39.0% of images but 77.0% of CLIP-assigned fantasy scenes. We then evaluate six frozen detectors at thresholds calibrated to a 5% flag rate on reference photographs. Collection flag rates range from 3.7 to 56.4%, falling 42-81 percentage points below GenImage recall. Held-out artwork false-positive rates range from 1.5 to 96.5%, so a higher collection flag rate does not by itself establish better detection. An exploratory X-only comparison with our April collection finds a higher September flag rate for Effort, and a suggestive difference for DoU, under fixed-threshold post-clustered bootstrap intervals. Attribution, content and processing differences prevent a causal interpretation of these contrasts. The collection supports analysis of reported model use during a product transition, with source and attribution evidence retained for interpretation.
Robust semantic watermarking method improves diffusion language model security
DenMark: Robust Semantic Watermarking for Diffusion Language Models
Abstract: Semantic text watermarks encode signals in meaning rather than surface token choices, offering robustness to paraphrasing and other semantic-preserving edits. Existing semantic watermarking methods are primarily designed for autoregressive language models (ARLMs), where completed candidate units can be generated and scored before generation proceeds. This paradigm does not naturally extend to diffusion language models (DLMs), where semantic units remain incomplete during intermediate denoising steps and tokens may be updated in flexible orders. We propose DenMark, a semantic watermarking framework that injects key-dependent signals directly into the DLM denoising process. DenMark partitions the output into fixed token regions and uses temporary rollouts as semantic lookahead: conditional completions estimate the eventual semantics of an incomplete region, enabling DenMark to select local updates with higher estimated semantic watermark scores. Repeating this procedure across denoising steps progressively accumulates watermark evidence in the final output. For detection, DenMark uses calibrated scanning over candidate unit sizes to remain robust to boundary shifts introduced by semantic attacks. Across four DLMs, three datasets, and four semantic attacks, DenMark achieves the best results across all reported detection metrics in all 48 backbone-dataset-attack combinations. These results demonstrate that DenMark provides an effective mechanism for robust semantic watermarking in DLMs.
ChatGPT Images 2.5 shows mixed results on image forgery tasks
From Advertised Improvements to Measured Capabilities: Evaluating ChatGPT Images 2.5 on Forgery Tasks
Abstract: We evaluate whether the improvements advertised for ChatGPT Images 2.5 translate into better performance on forgery tasks with predetermined answers. We compare its Flare and Sunburst API models with GPT-Image-2 re-run in the same week, using receipt-field edits, repeated editing, product placement and fine-print rendering. After image registration, Flare and Sunburst show fewer OCR-detected changes to surrounding receipt text (31.7% and 31.2% versus 44.2% for both GPT-Image-2 baselines), mainly on CORD receipts, without a detectable improvement in target-field correctness. Flare retains fewer earlier edits on CORD receipts, while photo-edit sequences provide little separation between models. Product codes are more often legible with Images 2.5, alongside larger product placement; the analyses do not establish a fidelity gain independent of size. Fine-print improvements remain unresolved below the OCR reliability limit. Refusals are rare and localisation is weak in both generations. At a fixed detection threshold, Community Forensics flags 68.6% of controlled Images 2.5 images averaged across cells, versus 35.9% of self-reported images posted online. These results motivate task-specific evaluation of advertised capabilities and defences, with explicit limits on what automatic checks can establish.