相关论文: ToDA: Target-oriented Diffusion Attacker against R…

Recommender systems (RSs) are now fundamental to various online platforms, but their dependence on user-contributed data leaves them vulnerable to shilling attacks that can manipulate item rankings by injecting fake users. Although widely…

The rapid advancement of diffusion models has enhanced their image inpainting and editing capabilities but also introduced significant societal risks. Adversaries can exploit user images from social media to generate misleading or harmful…

Guided image synthesis methods, like SDEdit based on the diffusion model, excel at creating realistic images from user inputs such as stroke paintings. However, existing efforts mainly focus on image quality, often overlooking a key point:…

Recommendation Systems (RS) have become an essential part of many online services. Due to its pivotal role in guiding customers towards purchasing, there is a natural motivation for unscrupulous parties to spoof RS for profits. In this…

Due to the pivotal role of Recommender Systems (RS) in guiding customers towards the purchase, there is a natural motivation for unscrupulous parties to spoof RS for profits. In this paper, we study Shilling Attack where an adversarial…

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic…

As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment. Despite its tremendous popularity, the…

Denoising probabilistic diffusion models have shown breakthrough performance to generate more photo-realistic images or human-level illustrations than the prior models such as GANs. This high image-generation capability has stimulated the…

Deep learning models in computational pathology often fail to generalize across cohorts and institutions due to domain shift. Existing approaches either fail to leverage unlabeled data from the target domain or rely on image-to-image…

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to…

Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient labeled data. The…

Recommender systems play a central role in digital platforms by providing personalized content. They often use methods such as collaborative filtering and machine learning to accurately predict user preferences. Although these systems offer…

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

Intrusion Detection Systems (IDSs) are a key component for protecting Internet of Things (IoT) environments. However, in Machine Learning-based (ML-based) IDSs, performance is often degraded by the strong class imbalance between benign and…

With the development of information technology and the Internet, recommendation systems have become an important means to solve the problem of information overload. However, recommendation system is greatly fragile as it relies heavily on…

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective,…

Jailbreak attacks exploit specific prompts to bypass LLM safeguards, causing the LLM to generate harmful, inappropriate, and misaligned content. Current jailbreaking methods rely heavily on carefully designed system prompts and numerous…

Recommender systems (RS) greatly influence users' consumption decisions, making them attractive targets for malicious shilling attacks that inject fake user profiles to manipulate recommendations. Existing shilling methods can generate…