# Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

arXiv: https://arxiv.org/abs/2604.10460 · HTML: https://mlsanity.com/paper/2604.10460/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 20 of 20)

- [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)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation](https://mlsanity.com/paper/1802.07228/) (2018)
- [Exploring Hate Speech Detection in Multimodal Publications](https://mlsanity.com/paper/1910.03814/) (2019)
- [The Creativity of Text-to-Image Generation](https://mlsanity.com/paper/2206.02904/) (2022)
- [A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations](https://mlsanity.com/paper/2502.14881/) (2025)
- [Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models](https://mlsanity.com/paper/2401.16727/) (2024)
- [Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs](https://mlsanity.com/paper/2502.11184/) (2025)
- [Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models](https://mlsanity.com/paper/2311.17394/) (2023)
- [Blessing or curse? A survey on the Impact of Generative AI on Fake News](https://mlsanity.com/paper/2404.03021/) (2024)
- [Real-Time Adversarial Attacks](https://mlsanity.com/paper/1905.13399/) (2019)
- [How Spammers and Scammers Leverage AI-Generated Images on Facebook for Audience Growth](https://mlsanity.com/paper/2403.12838/) (2024)
- [Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality](https://mlsanity.com/paper/2305.10547/) (2023)
- [Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs](https://mlsanity.com/paper/2601.06460/) (2026)

## Built on by (most cited first, 1 of 1)

- [LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models](https://mlsanity.com/paper/2604.18803/) (2026)

## Abstract (arXiv)

The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This contextual misuse undermines the traditional moderation framework and complicates attribution, as synthetic images typically lack persistent metadata or device signatures. We introduce a steganography enabled attribution framework that embeds cryptographically signed identifiers into images at creation time and uses multimodal harmful content detection as a trigger for attribution verification. Our system evaluates five watermarking methods across spatial, frequency, and wavelet domains. It also integrates a CLIP-based fusion model for multimodal harmful-content detection. Experiments demonstrate that spread-spectrum watermarking, especially in the wavelet domain, provides strong robustness under blur distortions, and our multimodal fusion detector achieves an AUC-ROC of 0.99, enabling reliable cross-modal attribution verification. These components form an end-to-end forensic pipeline that enables reliable tracing of harmful deployments of AI-generated imagery, supporting accountability in modern synthetic media environments. Our code is available at GitHub: https://github.com/bli1/steganography