mlsanityData to 7 Oct 2026

ALIEN: Analytic Latent Watermarking for Controllable Generation

arXiv 2602.06101 ↗First posted 5 Feb 2026eess.IV cs.CV cs.MMcited by 0

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models (LDMs) are considered a powerful tool for generative tasks. However, reliance on computationally intensive heuristic optimization for iterative signal refinement results in high training overhead and local optima entrapment.To address these issues, we propose an underlineAnaunderlinelytical Watermarkunderlineing Framework for Controllablunderlinee Generatiounderlinen (ALIEN). We develop the first analytical derivation of the time-dependent modulation coefficient that guides the diffusion of watermark residuals to achieve controllable watermark embedding pattern.Experimental results show that ALIEN-Q outperforms the state-of-the-art by 33.1% across 5 quality metrics, and ALIEN-R demonstrates 14.0% improved robustness against generative variant and stability threats compared to the state-of-the-art across 15 distinct conditions. Code can be available at https://anonymous.4open.science/r/ALIEN/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 34 of its 46 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

34 of 46 references.

Closest ancestors · 15

Same direction, newest first

  1. 2025Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity9 Sep
  2. 2025GaussMarker: Robust Dual-Domain Watermark for Diffusion Models13 Jun
  3. 2024SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models6 Dec
  4. 2024Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models4 Dec
  5. 2024SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI18 Nov
  6. 2024ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization6 Nov
  7. 2024An Undetectable Watermark for Generative Image Models9 Oct
  8. 2024LaWa: Using Latent Space for In-Generation Image Watermarking11 Aug
  9. 2024WMAdapter: Adding WaterMark Control to Latent Diffusion Models12 Jun
  10. 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA18 May
  11. 2024Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models7 Apr
  12. 2024Latent Watermark: Inject and Detect Watermarks in Latent Diffusion Space30 Mar
3 more
  1. 2024Attack-Resilient Image Watermarking Using Stable Diffusion8 Jan
  2. 2023Invisible Image Watermarks Are Provably Removable Using Generative AI2 Jun
  3. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Models27 Mar

Other references · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  11. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  12. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
7 more
  1. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  2. 2018Variational image compression with a scale hyperpriorcited by 910
  3. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  4. 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Datacited by 322
  5. 2019StegaStamp: Invisible Hyperlinks in Physical Photographscited by 256
  6. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
  7. 2024RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identificationcited by 87

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PhaseMark: A Post-hoc, Optimization-Free Watermarking of AI-generated Images in the Latent Frequency Domain
  2. 2025TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement
  3. 2026On the Intrinsic Limited Robustness of Latent-Based Watermarking
  4. 2024MarkPlugger: Generalizable Watermark Framework for Latent Diffusion Models without Retraining
  5. 2025SWA-LDM: Toward Stealthy Watermarks for Latent Diffusion Models
  6. 2025Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios
  7. 2026Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models
  8. 2024An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting