相关论文: Preference Redirection via Attention Concentration…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

To autonomously control vehicles, driving agents use outputs from a combination of machine-learning (ML) models, controller logic, and custom modules. Although numerous prior works have shown that adversarial examples can mislead ML models…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However,…

Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global…

Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks(DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in…

Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security…

Distributed multi-agent optimization (DMAO) enables the scalable control and coordination of a large population of edge resources in complex multi-agent environments. Despite its great scalability, DMAO is prone to cyber attacks as it…

Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become…

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

Deep recognition models are widely vulnerable to adversarial examples, which change the model output by adding quasi-imperceptible perturbation to the image input. Recently, Segment Anything Model (SAM) has emerged to become a popular…

Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…

Intrinsic susceptibility of deep learning to adversarial examples has led to a plethora of attack techniques with a broad common objective of fooling deep models. However, we find slight compositional differences between the algorithms…

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…

This work focuses on object goal visual navigation, aiming at finding the location of an object from a given class, where in each step the agent is provided with an egocentric RGB image of the scene. We propose to learn the agent's policy…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial…

Administrative Role Based Access Control (ARBAC) models deal with how to manage user-role assignments (URA), permission-role assignments (PRA), and role-role assignments (RRA). A wide variety of approaches has been proposed in the…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs) capable of automating diverse computer tasks. As their commercial potential grows, critical details of the most capable CUA systems remain…