中文
相关论文

相关论文: A Trajectory-Based Safety Audit of Clawdbot (OpenC…

200 篇论文

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

密码学与安全 · 计算机科学 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses…

计算与语言 · 计算机科学 2026-05-19 Chengzhi Liu , Yichen Guo , Yepeng Liu , Yuzhe Yang , Qianqi Yan , Xuandong Zhao , Wenyue Hua , Sheng Liu , Sharon Li , Yuheng Bu , Xin Eric Wang

Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…

密码学与安全 · 计算机科学 2026-03-20 Haochen Zhao , Shaoyang Cui

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

人工智能 · 计算机科学 2026-04-06 Yunhao Feng , Yifan Ding , Yingshui Tan , Xingjun Ma , Yige Li , Yutao Wu , Yifeng Gao , Kun Zhai , Yanming Guo

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…

计算与语言 · 计算机科学 2026-05-04 Prerna Juneja , Lika Lomidze

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

多智能体系统 · 计算机科学 2025-08-11 Alistair Reid , Simon O'Callaghan , Liam Carroll , Tiberio Caetano

Autonomous vehicles ought to predict the surrounding agents' trajectories to allow safe maneuvers in uncertain and complex traffic situations. As companies increasingly apply trajectory prediction in the real world, security becomes a…

机器学习 · 计算机科学 2024-01-04 Kaouther Messaoud , Kathrin Grosse , Mickael Chen , Matthieu Cord , Patrick Pérez , Alexandre Alahi

Millions of users turn to consumer AI chatbots to discuss mental health and behavioral concerns. While this presents unprecedented opportunities to deliver population-level support, it also highlights an urgent need for rigorous and…

神经元与认知 · 定量生物学 2026-03-10 Veith Weilnhammer , Kevin YC Hou , Lennart Luettgau , Christopher Summerfield , Raymond Dolan , Matthew M Nour

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…

计算与语言 · 计算机科学 2025-05-21 Zhexin Zhang , Shiyao Cui , Yida Lu , Jingzhuo Zhou , Junxiao Yang , Hongning Wang , Minlie Huang

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm…

计算机与社会 · 计算机科学 2026-02-24 Nelu D. Radpour

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.…

密码学与安全 · 计算机科学 2025-05-20 Mykyta Mudryi , Markiyan Chaklosh , Grzegorz Wójcik

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

密码学与安全 · 计算机科学 2026-05-13 Hongwei Yao , Yiming Liu , Yiling He , Bingrun Yang

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

密码学与安全 · 计算机科学 2025-09-10 Hongfei Xia , Hongru Wang , Zeming Liu , Qian Yu , Yuhang Guo , Haifeng Wang

Driving safety is a top priority for autonomous vehicles. Orthogonal to prior work handling accident-prone traffic events by algorithm designs at the policy level, we investigate a Closed-loop Adversarial Training (CAT) framework for safe…

机器学习 · 计算机科学 2023-10-20 Linrui Zhang , Zhenghao Peng , Quanyi Li , Bolei Zhou

EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…

密码学与安全 · 计算机科学 2026-03-12 Chaoyuan Peng , Lei Wu , Yajin Zhou

InvisibleBench is a deployment gate for caregiving-relationship AI, evaluating 3-20+ turn interactions across five dimensions: Safety, Compliance, Trauma-Informed Design, Belonging/Cultural Fitness, and Memory. The benchmark includes…

计算机与社会 · 计算机科学 2025-11-27 Ali Madad

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

机器学习 · 计算机科学 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv

In the last years, AI safety gained international recognition in the light of heterogeneous safety-critical and ethical issues that risk overshadowing the broad beneficial impacts of AI. In this context, the implementation of AI observatory…

计算机与社会 · 计算机科学 2020-12-08 Nadisha-Marie Aliman , Leon Kester , Roman Yampolskiy

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over…

计算与语言 · 计算机科学 2026-04-28 Suhas BN , Andrew M. Sherrill , Rosa I. Arriaga , Chris W. Wiese , Saeed Abdullah

As large language models (LLMs) continue to advance and gain influence, the development of embodied AI has accelerated, drawing significant attention, particularly in navigation scenarios. Embodied navigation requires an agent to perceive,…

人工智能 · 计算机科学 2025-08-11 Zixia Wang , Jia Hu , Ronghui Mu