Related papers: EIA: Environmental Injection Attack on Generalist …

AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human…

The emergence of Agentic Artificial Intelligence (AAI) systems capable of independently initiating digital interactions necessitates a new optimisation paradigm designed explicitly for seamless agent-platform interactions. This article…

Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…

This work investigates and evaluates multiple defense strategies against property inference attacks (PIAs), a privacy attack against machine learning models. Given a trained machine learning model, PIAs aim to extract statistical properties…

Modern AI-powered Integrated Development Environments (AI-IDEs) are increasingly defined by an Agent-centric architecture, where an LLM-powered Agent is deeply integrated to autonomously execute complex tasks. This tight integration,…

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving…

This paper introduces a novel attack vector that leverages website cloaking techniques to compromise autonomous web-browsing agents powered by Large Language Models (LLMs). As these agents become more prevalent, their unique and often…

As the social implementation of AI has been steadily progressing, research and development related to AI security has also been increasing. However, existing studies have been limited to organizing related techniques, attacks, defenses, and…

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…

The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…

The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where automated, AI-assisted attacks evolve continuously. Content Delivery Networks (CDNs) and edge…

Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion models (DMs) in image quality (FID: 1.48 vs. 1.58) while allowing for a higher generation…

In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency. As semantic communication relies on deep learning to extract meaning from raw messages, it is vulnerable to attacks…

Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…

While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap by assessing the privacy risks of fairness-enhanced binary…

Face images are rich data items that are useful and can easily be collected in many applications, such as in 1-to-1 face verification tasks in the domain of security and surveillance systems. Multiple methods have been proposed to protect…

Explainable Artificial Intelligence (XAI) is a crucial pathway in mitigating the risk of non-transparency in the decision-making process of black-box Artificial Intelligence (AI) systems. However, despite the benefits, XAI methods are found…

Personally identifiable information (PII) can find its way into cyberspace through various channels, and many potential sources can leak such information. Data sharing (e.g. cross-agency data sharing) for machine learning and analytics is…