相关论文: Reflected Search Poisoning for Illicit Promotion

In this study, we reveal, for the first time, popular online social networks (especially Twitter) are being extensively abused by miscreants to promote illicit goods and services of diverse categories. This study is made possible by…

Relative Path Overwrite (RPO) is a recent technique to inject style directives into sites even when no style sink or markup injection vulnerability is present. It exploits differences in how browsers and web servers interpret relative paths…

Modern recommender systems (RS) have profoundly enhanced user experience across digital platforms, yet they face significant threats from poisoning attacks. These attacks, aimed at manipulating recommendation outputs for unethical gains,…

News Recommendation System(NRS) has become a fundamental technology to many online news services. Meanwhile, several studies show that recommendation systems(RS) are vulnerable to data poisoning attacks, and the attackers have the ability…

Web spam refers to some techniques, which try to manipulate search engine ranking algorithms in order to raise web page position in search engine results. In the best case, spammers encourage viewers to visit their sites, and provide…

IP prefix hijacks allow adversaries to redirect and intercept traffic, posing a threat to the stability and security of the Internet. To prevent prefix hijacks, networks should deploy RPKI and filter bogus BGP announcements with invalid…

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Sequential recommender systems (SRSs) excel in capturing users' dynamic interests, thus playing a key role in various industrial applications. The popularity of SRSs has also driven emerging research on their security aspects, where data…

Recent advancements in Large Language Models (LLMs) have significantly enhanced the capabilities of AI-Powered Search Engines (AIPSEs), offering precise and efficient responses by integrating external databases with pre-existing knowledge.…

Recommender systems have become an integral part of online services to help users locate specific information in a sea of data. However, existing studies show that some recommender systems are vulnerable to poisoning attacks, particularly…

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…

The scarcity of data and the high complexity of Advanced Persistent Threats (APTs) attacks have created challenges in comprehending their behavior and hindered the exploration of effective detection techniques. To create an effective APT…

To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely adopted. However, integrating external tools expands the attack surface, exposing agents to…

Hidden links are designed solely for search engines rather than visitors. To get high search engine rankings, link hiding techniques are usually used for the profitability of black industries, such as illicit game servers, false medical…

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models (LLMs) to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are…

Large Language Model (LLM) agents relying on external retrieval are increasingly deployed in high-stakes environments. While existing adversarial attacks primarily focus on content falsification or instruction injection, we identify a…

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…

IP spoofing enables reflection and amplification attacks, which cause major threats to the current Internet infrastructure. Detecting IP packets with incorrect source addresses would help to improve the situation. This is easy at the…

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit…