English
Related papers

Related papers: Ctrl-Z: Controlling AI Agents via Resampling

200 papers

This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…

Cryptography and Security · Computer Science 2025-03-13 Halima I. Kure , Pradipta Sarkar , Ahmed B. Ndanusa , Augustine O. Nwajana

As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…

Cryptography and Security · Computer Science 2025-05-13 Krti Tallam

Translating statistical methods into reliable software is a persistent bottleneck in quantitative research. Existing AI code-generation tools produce code quickly but cannot guarantee faithful implementation -- a critical requirement for…

Software Engineering · Computer Science 2026-04-07 Tianzhu Qin , Yiqing Xu

Control applications present hard operational constraints. A violation of these can result in unsafe behavior. This paper introduces Safe Interactive Model Based Learning (SiMBL), a framework to refine an existing controller and a system…

Systems and Control · Electrical Eng. & Systems 2019-11-19 Marco Gallieri , Seyed Sina Mirrazavi Salehian , Nihat Engin Toklu , Alessio Quaglino , Jonathan Masci , Jan Koutník , Faustino Gomez

AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and…

Cryptography and Security · Computer Science 2026-05-15 Tianneng Shi , Jingxuan He , Zhun Wang , Hongwei Li , Linyu Wu , Wenbo Guo , Dawn Song

AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly…

Computation and Language · Computer Science 2024-09-18 Zachary S. Siegel , Sayash Kapoor , Nitya Nagdir , Benedikt Stroebl , Arvind Narayanan

Artificial intelligence (AI) is interacting with people at an unprecedented scale, offering new avenues for immense positive impact, but also raising widespread concerns around the potential for individual and societal harm. Today, the…

Artificial Intelligence · Computer Science 2024-06-25 Andrea Bajcsy , Jaime F. Fisac

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

Computers and Society · Computer Science 2026-03-17 Max Hellrigel-Holderbaum , Edward James Young

Recent progress in autonomous code generation has fueled excitement around AI agents capable of accelerating scientific discovery by running experiments. However, there is currently no benchmark that evaluates whether such agents can…

Artificial Intelligence · Computer Science 2025-06-25 Gyeongwon James Kim , Alex Wilf , Louis-Philippe Morency , Daniel Fried

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Physics and Society · Physics 2026-05-12 Giordano De Marzo , Alessandro Bellina , Claudio Castellano , Viola Priesemann , David Garcia

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…

Cryptography and Security · Computer Science 2026-02-13 Aashish Kolluri , Rishi Sharma , Manuel Costa , Boris Köpf , Tobias Nießen , Mark Russinovich , Shruti Tople , Santiago Zanella-Béguelin

Current tool-using AI agents suffer from limited action space, context inefficiency, and probabilistic instability that makes them unsuitable for handling repetitive tasks which are otherwise reliably and efficiently tackled by agentic…

Software Engineering · Computer Science 2025-12-19 Nishant Gaurav , Adit Akarsh , Tejas Ravishankar , Manoj Bajaj

Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…

Computers and Society · Computer Science 2026-03-26 Merlin Stein

There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely on self-reported user data or interviews, offering limited insights into real-time…

Computation and Language · Computer Science 2026-05-04 Prerna Juneja , Lika Lomidze

Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations,…

Artificial Intelligence · Computer Science 2024-12-06 David Piorkowski , Michael Hind , John Richards

Clinical trials constitute a critical yet exceptionally challenging and costly stage of drug development (\$2.6B per drug), where protocols are encoded as complex natural language documents, motivating the use of AI systems beyond manual…

Artificial Intelligence · Computer Science 2026-04-06 Sixue Xing , Kerui Wu , Xuanye Xia , Meng Jiang , Jintai Chen , Tianfan Fu

Creating systems that are aligned with our goals is seen as a leading approach to create safe and beneficial AI in both leading AI companies and the academic field of AI safety. We defend the view that misaligned AGI - future, generally…

Computers and Society · Computer Science 2025-06-05 Max Hellrigel-Holderbaum , Leonard Dung

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

Cryptography and Security · Computer Science 2025-06-02 Hanrong Zhang , Jingyuan Huang , Kai Mei , Yifei Yao , Zhenting Wang , Chenlu Zhan , Hongwei Wang , Yongfeng Zhang

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

Cryptography and Security · Computer Science 2025-05-20 Mykyta Mudryi , Markiyan Chaklosh , Grzegorz Wójcik

This study investigates the generation of unsafe or harmful content in state-of-the-art generative models, focusing on methods for restricting such generations. We introduce a novel training-free approach using attention reweighing to…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Shivank Garg , Manyana Tiwari