Related papers: WebSentinel: Detecting and Localizing Prompt Injec…

Cyber threat hunting is the practice of proactively searching for latent threats in a network. Engaging in threat hunting can be difficult due to the volume of network traffic, variety of adversary techniques, and constantly evolving…

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt…

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit…

Smart contracts on the blockchain offer decentralized financial services but often lack robust security measures, leading to significant economic losses. While substantial research has focused on identifying vulnerabilities in smart…

Underground pipeline leaks and infiltrations pose significant threats to water security and environmental safety. Traditional manual inspection methods provide limited coverage and delayed response, often missing critical anomalies. This…

Web attacks, i.e. attacks exclusively using the HTTP protocol, are rapidly becoming one of the fundamental threats for information systems connected to the Internet. When the attacks suffered by web servers through the years are analyzed,…

Collaborative spectrum sensing can significantly improve the detection performance of secondary unlicensed users (SUs). However, the performance of collaborative sensing is vulnerable to sensing data falsification attacks, where malicious…

The exponential growth of mobile devices has raised concerns about sensitive data leakage. In this paper, we make the first attempt to identify suspicious location-related HTTP transmission flows from the user's perspective, by answering…

Detecting spreading outbreaks in social networks with sensors is of great significance in applications. Inspired by the formation mechanism of human's physical sensations to external stimuli, we propose a new method to detect the influence…

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…

When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security threat. By injecting malicious instructions into the data that…

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this…

Botnets represent a global problem and are responsible for causing large financial and operational damage to their victims. They are implemented with evasion in mind, and aim at hiding their architecture and authors, making them difficult…

Subliminal prompting is a phenomenon in which language models are biased towards certain concepts or traits through prompting with semantically unrelated tokens. While prior work has examined subliminal prompting in user-LLM interactions,…

The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt injection, a simple yet effective method to mislead these models. We developed an algorithm for…

The services of internet place a key role in the daily life by enabling the in sequence from anywhere. To provide somewhere to stay the communication and management in applications the web services has stimulated to multitier design. In…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Web parameter injection attacks are common and powerful. In this kind of attacks, malicious attackers can employ HTTP requests to implement attacks against servers by injecting some malicious codes into the parameters of the HTTP requests.…