IRIS is a training‑free watermarking scheme for diffusion‑generated images that binds a watermark to the image’s visual semantics. It derives an intrinsic ring identifier from a content code of the non‑watermarked image and injects it late in the generation trajectory, ensuring the mark survives common processing while breaking under semantic changes or foreign images. Experiments on three prompt datasets show IRIS reliably detects watermarks, maintains fidelity to the original image, and resists forgery techniques that defeat other marks.
arXiv:2608. 10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored.
arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).
The paper introduces the concept of watermark laundering, where an attacker uses a single reconstruction prompt on public foundation image models to produce a visually faithful output that renders invisible watermarks undecodable. The authors evaluate this failure mode across six OpenAI and Google image editing models, three watermarking schemes, and 1,800 reconstructions, finding that OpenAI models cause the strongest payload disruption while Nano Banana 2 shows vulnerability of DwtDct under high-fidelity reconstruction. Prompt ablation experiments reveal that the disruption is driven by the reconstruction pathway itself rather than any specific removal instruction, highlighting prompt-conditioned reconstruction as a distinct attack interface.
arXiv:2603. 17531v2 Announce Type: replace-cross Abstract: Recent advancements in diffusion-based image editing pose a significant threat to the authenticity of digital visual content.
The paper introduces VeriFi, a watermarking framework that protects face images from AI‑generated manipulation. It embeds a compact semantic latent watermark to preserve content, localizes pixel‑level edits without explicit payloads, and simulates realistic deepfake attacks to improve robustness. Experiments on CelebA‑HQ and FFHQ show that VeriFi outperforms existing methods in robustness, localization accuracy, and recovery quality.
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.
arXiv:2608.29212v1 Announce Type: cross Abstract: Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore...
The paper introduces TaintedPixels, a proactive video‑protection technique that embeds subtle, structured perturbations into the blue channel of facial regions. These perturbations remain invisible in the original video but become noticeable after black‑box manipulation, thereby flagging deepfakes. Experiments on three off‑the‑shelf manipulation tools and two detectors show that TaintedPixels achieves the highest forgery detection rate while keeping visual distortion minimal (LPIPS = 0.0042), and a human study confirms that protected videos are rarely suspected, whereas forgeries from protected sources are identified as fake far more often than those from unprotected sources.
The paper introduces an adaptive embedding displacement attack (EDA) that exploits rewording, reordering, and resegmentation to remove semantic watermarks from text, achieving a 32.6%–47.9% success rate across four watermarking schemes. To counter this, the authors propose k‑SwordStamp, a semantic watermarking method that uses order‑robust detection over sub‑sentence units, significantly reducing vulnerability to structure‑based edits. Experiments show that EDA remains effective against k‑SwordStamp, but with a lower success rate (10.8%) compared to its performance on other schemes.
arXiv:2606. 28386v1 Announce Type: cross Abstract: Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the next-token prediction paradigm adapted from large language models.
Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations remains limited. Such transformations induce two fundamental failure modes: region removal, such as cropping or masking, which eliminates the information carried by removed pixels, and desynchronization, such as scaling or rotation, which misaligns pixel positions and disrupts decoding.
arXiv:2607. 26641v1 Announce Type: cross Abstract: Identity document (ID) authentication relies on the structural integrity of complex, high-frequency security patterns.