English
Related papers

Related papers: SafetyDrift: Predicting When AI Agents Cross the L…

200 papers

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…

Artificial Intelligence · Computer Science 2026-04-28 German Marin , Jatin Chaudhary

Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…

Logic in Computer Science · Computer Science 2026-03-24 Melwin Xavier , Vaisakh M A , Melveena Jolly , Midhun Xavier

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Computation and Language · Computer Science 2026-05-19 Nivya Talokar , Ayush K Tarun , Murari Mandal , Maksym Andriushchenko , Antoine Bosselut

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…

Cryptography and Security · Computer Science 2026-04-20 Xuwei Ding , Skylar Zhai , Linxin Song , Jiate Li , Taiwei Shi , Nicholas Meade , Siva Reddy , Jian Kang , Jieyu Zhao

Modern LLM agents solve complex tasks by operating in iterative execution loops, where they repeatedly reason, act, and self-evaluate progress to determine when a task is complete. In this work, we show that while this self-directed loop…

Cryptography and Security · Computer Science 2026-05-08 Huiyu Xu , Zhibo Wang , Wenhui Zhang , Ziqi Zhu , Yaopeng Wang , Kui Ren , Chun Chen

An OS kernel that runs LLM inference internally can read logit distributions before any text is generated and act on them as a governance primitive. This paper presents ProbeLogits, a kernel-level operation that performs a single forward…

Operating Systems · Computer Science 2026-04-21 Daeyeon Son

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

This paper puts forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unbounded number of exploratory trials. This is indeed possible,…

Systems and Control · Electrical Eng. & Systems 2023-02-14 Agustin Castellano , Hancheng Min , Juan Bazerque , Enrique Mallada

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

Cryptography and Security · Computer Science 2026-01-01 Yuan Xin , Dingfan Chen , Linyi Yang , Michael Backes , Xiao Zhang

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted…

Cryptography and Security · Computer Science 2025-10-09 Yixiang Zhang , Xinhao Deng , Zhongyi Gu , Yihao Chen , Ke Xu , Qi Li , Jianping Wu

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

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yuxiao Xiang , Junchi Chen , Zhenchao Jin , Changtao Miao , Haojie Yuan , Qi Chu , Tao Gong , Nenghai Yu

The rapid advancement of multi-modal large reasoning models (MLRMs) -- enhanced versions of multimodal language models (MLLMs) equipped with reasoning capabilities -- has revolutionized diverse applications. However, their safety…

Machine Learning · Computer Science 2025-04-15 Junfeng Fang , Yukai Wang , Ruipeng Wang , Zijun Yao , Kun Wang , An Zhang , Xiang Wang , Tat-Seng Chua

Load safety assessment and compliance is an essential step in the corporate process of every logistics service provider. In 2020, a total of 11,371 police checks of trucks were carried out, during which 9.6% (1091) violations against the…

Artificial Intelligence · Computer Science 2023-11-08 Julius Schöning , Niklas Kruse

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but…

Computation and Language · Computer Science 2026-04-22 Ishita Kakkar , Enze Zhang , Rheeya Uppaal , Junjie Hu

As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…

Computation and Language · Computer Science 2025-05-21 Zhexin Zhang , Shiyao Cui , Yida Lu , Jingzhuo Zhou , Junxiao Yang , Hongning Wang , Minlie Huang

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Human-Computer Interaction · Computer Science 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

Computation and Language · Computer Science 2024-06-14 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Yongbin Li

World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic AI. By predicting future states in compressed latent spaces,…

Cryptography and Security · Computer Science 2026-04-08 Manoj Parmar