相关论文: MirrorGuard: Toward Secure Computer-Use Agents via…
As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…
The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…
Guardian models play a crucial role in ensuring the safety and ethical behavior of user-facing AI applications by enforcing guardrails and detecting harmful content. While standard guardian models are limited to predefined, static harm…
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails,…
Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes…
Mobile graphical user interface (GUI) agents driven by vision-language models (VLMs) perceive the screen as rendered pixels and choose actions from what they see, so they cannot reliably separate trusted interface elements from…
The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI…
Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where…
Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful and benign prompts.…
The power grid is a critical infrastructure essential for public safety and welfare. As its reliance on digital technologies grows, so do its vulnerabilities to sophisticated cyber threats, which could severely disrupt operations. Effective…
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…
Computer agents powered by vision-language models (VLMs) have significantly advanced human-computer interaction, enabling users to perform complex tasks through natural language instructions. However, these agents are vulnerable to context…
A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…
Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex criminal activity. Working with law enforcement and policy…
Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior…
We introduce GUI-360$^\circ$, a large-scale, comprehensive dataset and benchmark suite designed to advance computer-using agents (CUAs). CUAs present unique challenges and is constrained by three persistent gaps: a scarcity of real-world…
While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text. Existing defensive…
The misuse of deep learning-based facial manipulation poses a significant threat to civil rights. To prevent this fraud at its source, proactive defense has been proposed to disrupt the manipulation process by adding invisible adversarial…