相关论文: Controllable and Stealthy Shilling Attacks via Dis…

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users' broad interests based on the filtered historical…

In this paper, we consider the resilient multi-dimensional consensus and distributed optimization problems of multi-agent systems (MASs) in the presence of both agent-based and denial-of-service (DoS) attacks. The considered agent-based…

Visually-aware recommender systems have found widespread application in domains where visual elements significantly contribute to the inference of users' potential preferences. While the incorporation of visual information holds the promise…

Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. As LLMs become more powerful, studying jailbreak methods is critical to…

Review-Based Recommender Systems (RBRS) have attracted increasing research interest due to their ability to alleviate well-known cold-start problems. RBRS utilizes reviews to construct the user and items representations. However, in this…

Local differential privacy (LDP) involves users perturbing their inputs to provide plausible deniability of their data. However, this also makes LDP vulnerable to poisoning attacks. In this paper, we first introduce novel poisoning attacks…

Although Deep Neural Networks (DNN) have become the backbone technology of several ubiquitous applications, their deployment in resource-constrained machines, e.g., Internet of Things (IoT) devices, is still challenging. To satisfy the…

Since it is impossible to predict and identify all the vulnerabilities of a network beforehand, and penetration into a system by malicious intruders cannot always be prevented, intrusion detection systems (IDSs) are essential entities to…

Reranking plays a crucial role in modern multi-stage recommender systems by rearranging the initial ranking list to model interplay between items. Considering the inherent challenges of reranking such as combinatorial searching space, some…

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object.…

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential…

Existing data-driven control methods generally do not address False Data Injection (FDI) and Denial-of-Service (DoS) attacks simultaneously. This letter introduces a distributed data-driven attack-resilient consensus problem under both FDI…

Diffusion models have become a central tool in deep generative modeling, but standard formulations rely on a single network and a single diffusion schedule to transform a simple prior, typically a standard normal distribution, into the…

Software Defined Networking (SDN) enables flexible and scalable network control and management. However, it also introduces new vulnerabilities that can be exploited by attackers. In particular, low-rate and slow or stealthy…

Since DNN is vulnerable to carefully crafted adversarial examples, adversarial attack on LiDAR sensors have been extensively studied. We introduce a robust black-box attack dubbed LiDAttack. It utilizes a genetic algorithm with a simulated…

Recommender systems, inferring users' preferences from their historical activities and personal profiles, have been an enormous success in the last several years. Most of the existing works are based on the similarities of users, objects or…

Black-box adversarial attacks remain challenging due to limited access to model internals. Existing methods often depend on specific network architectures or require numerous queries, resulting in limited cross-architecture transferability…

Deepfake detection faces a critical generalization hurdle, with performance deteriorating when there is a mismatch between the distributions of training and testing data. A broadly received explanation is the tendency of these detectors to…