Related papers: Visual Confused Deputy: Exploiting and Defending P…
Navigation is an essential ability for mobile agents to be completely autonomous and able to perform complex actions. However, the problem of navigation for agents with limited (or no) perception of the world, or devoid of a fully defined…
Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger…
Autonomous Vehicles (AVs) rely on individual perception systems to navigate safely. However, these systems face significant challenges in adverse weather conditions, complex road geometries, and dense traffic scenarios. Cooperative…
Visual illusions allow researchers to devise and test new models of visual perception. Here we show that artificial neural networks trained for basic visual tasks in natural images are deceived by brightness and color illusions, having a…
In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision. UFO employs a dual-agent framework to meticulously observe and analyze the…
Embodied agents in vision navigation coupled with deep neural networks have attracted increasing attention. However, deep neural networks have been shown vulnerable to malicious adversarial noises, which may potentially cause catastrophic…
General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…
CNN image classifiers are widely used, thanks to their efficiency and accuracy. However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general…
Camouflaged Object Detection (COD), the task of identifying objects concealed within their environments, has seen rapid growth due to its wide range of practical applications. A key step toward developing trustworthy COD systems is the…
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…
Deep neural network based object detection hasbecome the cornerstone of many real-world applications. Alongwith this success comes concerns about its vulnerability tomalicious attacks. To gain more insight into this issue, we proposea…
Ensuring the correct visual appearance of graphical user interfaces (GUIs) is important because visual bugs can cause substantial losses for businesses. An application might behave functionally correct in an automated test, but visual bugs…
Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing research focuses on online settings, desktop environments,…
Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape…
While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…
Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps.…
The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…
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…
Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…