Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block inappropriate prompts or erase sensitive concepts from the models. However, all the existing defense methods are not well prepared to handle diverse adversarial prompts. In this work, we introduce MacPrompt, a novel black-box and cross-lingual attack that reveals previously overlooked vulnerabilities in T2I safety mechanisms. Unlike existing attacks that rely on synonym substitution or prompt obfuscation, MacPrompt constructs macaronic adversarial prompts by performing cross-lingual character-level recombination of harmful terms, enabling fine-grained control over both semantics and appearance. By leveraging this design, MacPrompt crafts prompts with high semantic similarity to the original harmful inputs (up to 0.96) while bypassing major safety filters (up to 100%). More critically, it achieves attack success rates as high as 92% for sex-related content and 90\% for violence, effectively breaking even state-of-the-art concept removal defenses. These results underscore the pressing need to reassess the robustness of existing T2I safety mechanisms against linguistically diverse and fine-grained adversarial strategies. Warning: This paper includes sensitive examples (e.g., adult, violent, or illegal content). Unsafe images are masked but may still be disturbing.

With the rapid development of the internet, sharing photos through Social Network Platforms (SNPs) has become a new way for people to socialize, which poses serious threats to personal privacy. Recently, a thumbnail-preserving image privacy protection technique has emerged and garnered widespread attention. However, the existing schemes based on this technique often introduce noticeable noise into the protected image, resulting in poor visual quality. Motivated by the observation that a latent vector can be decoupled into the detail and contour components, in this paper, we propose HIPP, a thumbnail-preserving image privacy protection scheme that decouples the detail and contour information contained in the latent vector corresponding to the original image and reconstructs details by generation model. As a result, the generated protected image appears natural and has a thumbnail similar to the original one. Moreover, the protected images can be restored to versions that are indistinguishable from the original images. Experiments on CelebA, Helen, and LSUN datasets show that the SSIM between the restored and original images achieves 0.9899. Furthermore, compared to the previous works, HIPP achieves the lowest runtime and file expansion rate, with values of 0.07 seconds and 1.1046, respectively.

The pervasive prevalence of DeepFakes poses a profound threat to individual privacy and the stability of society. Believing the synthetic videos of a celebrity and trumping up impersonated forgery videos as authentic are just a few consequences generated by DeepFakes. We investigate current detectors that blindly deploy deep learning techniques that are not effective in capturing subtle clues of forgery when generative models produce remarkably realistic faces. Inspired by the fact that synthetic operations inevitably modify the regions of eyes and mouth to match the target face with the identity or expression of the source face, we conjecture that the continuity of facial movement patterns representing expressions that existed in the veritable faces will be disrupted or completely broken in synthetic faces, making it a potentially formidable indicator for DeepFake detection. To prove this conjecture, we utilize a dual‐branch network to capture the inconsistent patterns of facial movements within eyes and mouth regions separately. Extensive experiments on popular FaceForensics++, Celeb‐DF‐v1, Celeb‐DF‐v2, and DFDC‐Preview datasets have demonstrated not only effectiveness but also the robust capability of our method to outperform the state‐of‐the‐art baselines. Moreover, this work represents greater robustness against adversarial attacks, achieving ASR of 54.8% in the I‐FGSM attack and 43.1% in the PGD attack on the DeepFakes dataset of FaceForensics++, respectively.

As an increasing number of people tend to upload personal images to cloud platforms such as iCloud, Google Drive, and Baidu Cloud, the issue of image privacy protection in clouds has attracted widespread attention. Thumbnail-preserving encryption (TPE) is a newly proposed technology especially for balancing usability and privacy of images stored in clouds. The TPE-encrypted image does not reveal anything other than the thumbnail and size of the original one. Although many well-designed TPE schemes have been put forward, they almost all operate in the spatial domain and are not compatible with JPEG images. The only two schemes that can be applied in the frequency domain were proposed by Wright et al. and Marohn et al., but both of them have disadvantages and do not consider non-visual usability. In this paper, we propose a usability enhanced TPE scheme especially for JPEG images by utilizing reversible data hiding and image encryption in the frequency domain. We first transform the original image into the frequency domain and select some specific locations for extra information recording in every block. The original coefficient values at the selected locations are then collected and embedded into the rest of the block before encryption. Finally, the extra information is expected to be recorded into the selected locations of every block for non-visual usability. Experiments confirm that the proposed scheme achieves the target of balancing enhanced usability and privacy.

The number of images produced by people everyday is rapidly increasing in recent years and their local storage space may be not big enough for storing all these images. As a result, people are currently accustomed to uploading images to cloud platforms, which raises privacy concerns. Traditional image encryption is a way to protect image privacy without preserving visual usability, so that image owners fail to conveniently browse and manage their images stored in the cloud. Hence some visual privacy protection schemes were proposed to balance image privacy and usability, while many of them are irreversible. Recently, a novel reversible technology, called Thumbnail-Preserving Encryption (TPE), has been a hot topic. However, existing TPE schemes are either inefficient, or cannot perfectly restore the original image and meanwhile achieve Nonce-Respecting (NR) security. In view of this, we propose a reversible framework for efficient and secure visual privacy protection, which tunably preserves image visual usability for image owners with the idea of data hiding. In the framework, the original image is firstly divided into several regions by our proposed region division methods and one of the regions is vacated by data hiding. Then, the vacated region is utilized to preserve the original thumbnail by pixel adjustment after image encryption. Finally, pixels in each sub block are permuted for security. According to our theoretical analysis, the above processes are completely reversible and the processed image achieves NR security. Furthermore, we conduct extensive experiments, including recognition by various application programming interfaces, user surveys, and efficiency comparison, to demonstrate that our framework is efficient and strikes a good balance between privacy and usability.