English
Related papers

Related papers: Async Control: Stress-testing Asynchronous Control…

200 papers

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Cryptography and Security · Computer Science 2026-04-07 Khanh Linh Nguyen , Hoa Nghiem , Tu Tran

Agents aspire to eliminate the need for task-specific prompt crafting through autonomous reason-act-observe loops. Still, they are commonly instructed to follow a task-specific plan for guidance, e.g., to resolve software issues following…

Software Engineering · Computer Science 2026-04-29 Shuyang Liu , Saman Dehghan , Jatin Ganhotra , Martin Hirzel , Reyhaneh Jabbarvand

Supercomputers have revolutionized how industries and scientific fields process large amounts of data. These machines group hundreds or thousands of computing nodes working together to execute time-consuming programs that require a large…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-01-24 João B. Fernandes , Ítalo A. S. de Assis , Idalmis M. S. Martins , Tiago Barros , Samuel Xavier-de-Souza

Existing works on multi-agent time-varying optimization allow agents to asynchronously communicate and/or compute, but do not allow asynchronous sampling of objectives. Sampling can be difficult to synchronize, and we therefore present a…

Optimization and Control · Mathematics 2025-08-21 Gabriel Behrendt , Zachary I. Bell , Matthew Hale

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…

Cryptography and Security · Computer Science 2025-06-12 Li Changjiang , Liang Jiacheng , Cao Bochuan , Chen Jinghui , Wang Ting

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Machine Learning · Computer Science 2026-02-24 Tim Beyer , Yan Scholten , Leo Schwinn , Stephan Günnemann

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Machine Learning · Computer Science 2025-06-26 Mahdi Sabbaghi , Paul Kassianik , George Pappas , Yaron Singer , Amin Karbasi , Hamed Hassani

Shared resource interference is observed by applications as dynamic performance asymmetry. Prior art has developed approaches to reduce the impact of performance asymmetry mainly at the operating system and architectural levels. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-24 Jing Chen , Pirah Noor Soomro , Mustafa Abduljabbar , Madhavan Manivannan , Miquel Pericas

We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomous) cyber-physical systems because of their ability to solve…

Machine Learning · Computer Science 2026-04-03 Alejandro Luque-Cerpa , Mengyuan Wang , Emil Carlsson , Sanjit A. Seshia , Devdatt Dubhashi , Hazem Torfah

In this paper, the synchronization of heterogeneous agents interacting over a dynamical network is studied. The edge dynamics can model the inter-agent communications which are often heterogeneous by nature. They can also model the…

Systems and Control · Electrical Eng. & Systems 2022-11-09 Dan Wang , Wei Chen , Li Qiu

With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…

Cryptography and Security · Computer Science 2025-11-03 Sheng Yin , Xianghe Pang , Yuanzhuo Ding , Menglan Chen , Yutong Bi , Yichen Xiong , Wenhao Huang , Zhen Xiang , Jing Shao , Siheng Chen

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Cryptography and Security · Computer Science 2026-04-08 Zenghao Duan , Yuxin Tian , Zhiyi Yin , Liang Pang , Jingcheng Deng , Zihao Wei , Shicheng Xu , Yuyao Ge , Xueqi Cheng

Cyber-physical systems can be subject to sensor attacks, e.g., sensor spoofing, leading to unsafe behaviors. This paper addresses this problem in the context of linear systems when an omniscient attacker can spoof several system sensors at…

Systems and Control · Electrical Eng. & Systems 2024-09-16 Xiao Tan , Pio Ong , Paulo Tabuada , Aaron D. Ames

Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. These agents can extend the base LLM's capabilities in multiple ways. For example,…

Cryptography and Security · Computer Science 2024-07-31 Boyang Zhang , Yicong Tan , Yun Shen , Ahmed Salem , Michael Backes , Savvas Zannettou , Yang Zhang

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

Artificial Intelligence · Computer Science 2026-03-30 Haoyu Wang , Christopher M. Poskitt , Jiali Wei , Jun Sun

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

Artificial Intelligence · Computer Science 2025-05-21 Vu Dinh Xuan , Hao Vo , David Murphy , Hoang D. Nguyen

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Machine Learning · Computer Science 2026-04-02 Aengus Lynch

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…

Artificial Intelligence · Computer Science 2026-05-29 Jianshuo Dong , Sheng Guo , Hao Wang , Xun Chen , Zhuotao Liu , Tianwei Zhang , Ke Xu , Minlie Huang , Han Qiu

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

Cryptography and Security · Computer Science 2026-02-03 Liming Lu , Xiang Gu , Junyu Huang , Jiawei Du , Xu Zheng , Yunhuai Liu , Yongbin Zhou , Shuchao Pang

We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from…

Artificial Intelligence · Computer Science 2026-05-18 Parand A. Alamdari , Toryn Q. Klassen , Sheila A. McIlraith