Related papers: Low Resource Reconstruction Attacks Through Benign…
Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally…
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…
Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…
The generation of high-quality images has become widely accessible and is a rapidly evolving process. As a result, anyone can generate images that are indistinguishable from real ones. This leads to a wide range of applications, including…
Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and financial platforms. To comply with privacy regulations like the GDPR, CCPA, and PIPEDA,…
Face anti-spoofing is a critical technology for ensuring the security of face recognition systems. However, its ability to generalize across diverse scenarios remains a significant challenge. In this paper, we attribute the limited…
Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…
Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resulting in undesirable reconstruction. However, increasing the…
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely…
Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Text-to-Image (T2I) diffusion models are widely recognized for their ability to generate high-quality and diverse images based on text prompts. However, despite recent advances, these models are still prone to generating unsafe images…
Conditional generative models such as DALL-E and Stable Diffusion generate images based on a user-defined text, the prompt. Finding and refining prompts that produce a desired image has become the art of prompt engineering. Generative…
Deep learning models are increasingly deployed in real-world applications. These models are often deployed on the server-side and receive user data in an information-rich representation to solve a specific task, such as image…
Federated learning (FL) enables decentralized machine learning without sharing raw data, allowing multiple clients to collaboratively learn a global model. However, studies reveal that privacy leakage is possible under commonly adopted FL…
Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…
Modern text-to-image (T2I) generation systems (e.g., DALL$\cdot$E 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation. Despite its practicality, the security analyses of this…
With the randomization approach, sensitive data items of records are randomized to protect privacy of individuals while allowing the distribution information to be reconstructed for data analysis. In this paper, we distinguish between…
Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…
Blind face restoration aims to recover high-quality facial images from various unidentified sources of degradation, posing significant challenges due to the minimal information retrievable from the degraded images. Prior knowledge-based…