Spam detection in the physical world

Disrupting malicious uses of AI: June 2025

Our latest report featuring case studies of how we’re detecting and preventing malicious uses of AI.

Robots that learn

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.

Physical AI: What It Is and What It Is Not

A quick guide to separating Physical AI from world models, embodied AI, physics AI, and digital twins The post Physical AI: What It Is and What It Is Not appeared first on Towards Data Science .

Targeting World Models to Compromise Robot Learning Pipelines

arXiv:2606. 09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline.

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

arXiv:2607. 04146v1 Announce Type: cross Abstract: This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics ecosystem holds trust assumptions about community contributions.

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems

arXiv:2608. 00747v2 Announce Type: replace-cross Abstract: Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe decisions and physical harm.

Disrupting malicious uses of AI

Artificially intelligent agents in the social and behavioral sciences: A history and outlook

arXiv:2510. 05743v3 Announce Type: replace Abstract: We review the historical development and current trends of artificially intelligent agents (agentic AI) in the social and behavioral sciences: from the first programmable computers, and social simulations soon thereafter, to today's experiments with large language models.

What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation

arXiv:2607. 26935v1 Announce Type: new Abstract: Bot detectors deployed at scale treat traffic as binary: human or bot.

MuTRAP: Multi-trigger Trojans Attacking Robot Task Planning Systems

arXiv:2504. 17070v3 Announce Type: replace-cross Abstract: Robots need task planning methods to achieve goals that require more than one action.

Disrupting malicious uses of AI: October 2025

Discover how OpenAI is detecting and disrupting malicious uses of AI in our October 2025 report. Learn how we’re countering misuse, enforcing policies, and protecting users from real-world harms.

Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring

arXiv:2607. 02121v1 Announce Type: cross Abstract: As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical.