CORTEXA
← Browse
arxivcs.CRcs.CV2026-06-29

Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective

Cheng-Yi Lee, Yichi Zhang, Yuchen Yang, Chun-Shien Lu, Jun-Cheng Chen

Recent studies have shown that semantic watermarks, which embed information into the initial noise of latent diffusion models (LDMs), are vulnerable to black-box forgery attacks. However, existing methods primarily rely on empirical evidence and lack a rigorous theoretical understanding of the conditions under which such attacks succeed or fail. To bridge this gap, we rethink the nature of such attacks through the lens of rate-distortion in the latent space. Our analysis identifies an irreducible distortion floor due to structural mismatches between proxy and target models, which fundamentally limits the fidelity of forged watermarks. We further characterize this distortion as structured geometric deviations on the latent manifold, in the form of global drift and local deformation rather than stochastic noise. Leveraging these insights, we propose a scheme-agnostic detection method that distinguishes forged samples before watermark verification. Extensive experiments demonstrate the effectiveness of our method across diverse black-box scenarios, while preserving robustness to common distortions.

View free PDFSource page

Related papers

arxivcs.CRcs.CVcs.LG2026-07-17

Do Agents Dream of False Memories? Black-box Visual Attacks on Long-term Memory in Multimodal AI Agents

Halima Bouzidi, Mboutidem Ekemini Mkpong, Mohammad Abdullah Al Faruque

Multimodal AI agents increasingly rely on persistent long-term memory to ground generation in past visual and textual episodes. We show that unconditional trust in visual data creates a critical vulnerability. We propose Lucid, a black-box adversarial framework that compromises m…

View free PDFSource page
arxivcs.CVcs.CR2026-06-28

The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

Tuo Chen, Minjing Dong, Benlei Cui, Jian Liu, Jie Gui

Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor attacks. Existing defenses struggle to defend against such attacks in a fully black-box setting because they often require acce…

View free PDFSource page
arxivcs.CRcs.AIcs.CV2026-07-02

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models

Zikai Zhang, Rui Hu, Olivera Kotevska, Jiahao Xu

Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing…

View free PDFSource page
arxivcs.CVcs.CR2026-07-10

Banshee: Target Switch Attacks on Gimbal-Stabilized Visual Tracking Systems via Acoustic Injection

Jiarui Li, Joseph Brewington, Qingzhao Zhang, Z. Morley Mao

Gimbal-stabilized visual tracking is critical for modern autonomous systems such as Unmanned Aerial Vehicles (UAVs). While prior work shows acoustic signals can disturb gimbal internals, the impact of such attacks on real-world applications like UAV tracking and following remains…

View free PDFSource page
arxivcs.CRcs.CV2026-07-01

From Forgeries to Foundation Models: A Systematic Survey of Identity Document Attack and Detection

Gourab Das, Pavan Kumar C, Raghavendra Ramachandra

Identity document forgery has undergone a fundamental capability shift: generative AI tools now enable high-fidelity document synthesis and field-level manipulation with minimal technical expertise, while detection methods remain constrained by benchmarks that do not reflect this…

View free PDFSource page
arxivcs.CVcs.CR2026-07-24

Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models

Yebin Zheng, Haonan An, Guang Hua, Zhiping Lin, Yuguang Fang

Latent domain watermarking for diffusion models embeds watermarks directly into the latent prior, enjoying non-intrusiveness to model parameters and seamless integration with the generation process. However, due to the violation of latent Gaussianity or sensitivity to normal and…

View free PDFSource page