Related papers: Environmental Injection Attacks against GUI Agents…
Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental…
Current frameworks for training offensive penetration testing agents with deep reinforcement learning struggle to produce agents that perform well in real-world scenarios, due to the reality gap in simulation-based frameworks and the lack…
The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive…
The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…
This work presents a threat modelling approach to represent changes to the attack paths through an Internet of Things (IoT) environment when the environment changes dynamically, i.e., when new devices are added or removed from the system or…
The transition to smart grids has increased the vulnerability of electrical power systems to advanced cyber threats. To safeguard these systems, comprehensive security measures-including preventive, detective, and reactive strategies-are…
Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention. Despite the impressive progress, the research question…
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…
Graphical User Interface (GUI) agents show promising capabilities for automating computer-use tasks and facilitating accessibility, but existing interactive benchmarks are mostly English-only, covering web-use or Windows, Linux, and Android…
Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints, and scarce…
Browser-using agents (BUAs) are an emerging class of AI agents that interact with web browsers in human-like ways, including clicking, scrolling, filling forms, and navigating across pages. While these agents help automate repetitive online…
Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses,…
The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human activity understanding. However, the reliability of these systems is critically undermined by…
Augmented reality (AR) enhances user interaction with the real world but also presents vulnerabilities, particularly through Visual Information Manipulation (VIM) attacks. These attacks alter important real-world visual cues, leading to…
Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications is hindered by high latency, poor reproducibility, and…
In the age of AI-powered educational (AIED) innovation, evaluating the developmental consequences of novel designs before they are exposed to students has become both essential and challenging. Since such interventions may carry…
While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains largely unexplored whether these simulations can replicate realistic structural and…
Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and…