Related papers: Avengers Ensemble! Improving Transferability of Au…

Facial stylization aims to transform facial images into appealing, high-quality stylized portraits, with the critical challenge of accurately learning the target style while maintaining content consistency with the original image. Although…

Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images…

Diffusion models, known for their tremendous ability to generate high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy risks. Recent methods for memory mitigation have primarily…

Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy protection; nevertheless, object recognition research typically assumes access to complete, unobfuscated images. In this paper, we explore the effects…

In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs…

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…

Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of unauthorized art style images for AST may infringe on…

Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…

In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the…

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…

As billions of personal data being shared through social media and network, the data privacy and security have drawn an increasing attention. Several attempts have been made to alleviate the leakage of identity information from face photos,…

In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the…

We present a novel black-box jailbreaking framework that integrates multiple LLM-as-Attacker strategies to deliver highly transferable and effective attacks. The framework is grounded in three key insights from prior jailbreaking research…

AI-generated images have become increasingly realistic and have garnered significant public attention. While synthetic images are intriguing due to their realism, they also pose an important misinformation threat. To address this new…

Growing applications of generative models have led to new threats such as malicious personation and digital copyright infringement. One solution to these threats is model attribution, i.e., the identification of user-end models where the…

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by…

The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated…

Diffusion models have attracted significant attention due to its exceptional data generation capabilities in fields such as image synthesis. However, recent studies have shown that diffusion models are vulnerable to copyright infringement…