# DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection

arXiv: https://arxiv.org/abs/2607.22035 · HTML: https://mlsanity.com/paper/2607.22035/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [On Second-Order Group Influence Functions for Black-Box Predictions](https://mlsanity.com/paper/1911.00418/) (2019)
- [Influence Functions for Scalable Data Attribution in Diffusion Models](https://mlsanity.com/paper/2410.13850/) (2024)
- [Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models](https://mlsanity.com/paper/2410.18639/) (2024)
- [Evaluating and Mitigating IP Infringement in Visual Generative AI](https://mlsanity.com/paper/2406.04662/) (2024)
- [A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models](https://mlsanity.com/paper/2403.12052/) (2024)
- [Can Large Vision-Language Models Detect Images Copyright Infringement from GenAI?](https://mlsanity.com/paper/2502.16618/) (2025)
- [SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2509.05625/) (2025)
- [Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy](https://mlsanity.com/paper/2509.23022/) (2025)

## Abstract (arXiv)

Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization. In this paper, we develops a unified post-hoc detection framework that treats copyright infringement evidence as a counterfactual conditional distribution shift: a protected target is suspicious when the model's behavior under aligned conditions would change measurably if that target were included in, or removed from, the training process. We formalize this view through conditional differential privacy and introduce Dual-Branch Conditional Sensitivity (DCS), an operational statistic that measures the observable gap between two locally perturbed model states. Specifically, the proposed DCS framework creates a learning branch and an unlearning branch around the deployed model, connects their displacement to the unavailable counterfactual retraining effect through influence-function analysis, and bounds the observable sensitivity by the counterfactual privacy-budget surrogate, local curvature, training-set scale, and perturbation step size. To distinguish target-specific memorization from generic fine-tuning instability, we further define a calibrated detection statistic that subtracts the sensitivity measured under orthogonal conditions. The DCS framework is instantiated for ridge-regularized linear regression, conditional diffusion models, autoregressive language models, and multimodal models. These instantiations show how the same principle can be evaluated through prediction gaps, image-embedding divergence, token-distribution or entropy shifts, and cross-modal representation changes.