Related papers: MirrorGuard: Toward Secure Computer-Use Agents via…
We observe a change in the way users access information, that is, the rise of conversational information access (CIA) agents. However, the automatic evaluation of these agents remains an open challenge. Moreover, the training of CIA agents…
The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose a novel and effective Neuron-Guided Defense method named…
Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…
While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…
LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly shapes subsequent actions. Small deviations in these thoughts can therefore propagate into…
The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust.…
The integration of Large Language Models (LLMs) into cybersecurity education for criminal justice professionals is currently hindered by the "statelessness" of reactive chatbots and the risk of hallucinations in high-stakes legal contexts.…
Augmented Reality (AR) enriches human perception by overlaying virtual elements onto the physical world. However, this tight coupling between virtual and real content makes AR vulnerable to cognitive attacks: manipulations that distort…
This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environments. The framework is underpinned by following six key…
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…
Integrating mixed reality (MR) with artificial intelligence (AI) technologies, including vision, language, audio, reasoning, and planning, enables the AI-powered MR assistant [1] to substantially elevate human efficiency. This enhancement…
Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these…
Multimodal Large Language Models (MLLMs) have significantly advanced GUI agents, yet long-horizon automation remains constrained by two critical bottlenecks: context overload from raw sequential trajectory dependence and architectural…
Large Language Models (LLMs) have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent built on top of…
Micro-controller units (MCUs) implement the de facto interface between the physical and digital worlds. As a consequence, they appear in a variety of sensing/actuation applications, from smart personal spaces to complex industrial control…
Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…
Although numerous strategies have recently been proposed to enhance the autonomous interaction capabilities of multimodal agents in graphical user interface (GUI), their reliability remains limited when faced with complex or out-of-domain…
Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…
Advancements in multimodal foundation models have enabled the development of Computer Use Agents (CUAs) capable of autonomously interacting with GUI environments. As CUAs are not restricted to certain tools, they allow to automate more…