English
Related papers

Related papers: Owner-Harm: A Missing Threat Model for AI Agent Sa…

200 papers

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…

Cryptography and Security · Computer Science 2026-05-18 Debeshee Das , Julien Piet , Darya Kaviani , Luca Beurer-Kellner , Florian Tramèr , David Wagner

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models.…

Computation and Language · Computer Science 2024-05-15 Bertie Vidgen , Adarsh Agrawal , Ahmed M. Ahmed , Victor Akinwande , Namir Al-Nuaimi , Najla Alfaraj , Elie Alhajjar , Lora Aroyo , Trupti Bavalatti , Max Bartolo , Borhane Blili-Hamelin , Kurt Bollacker , Rishi Bomassani , Marisa Ferrara Boston , Siméon Campos , Kal Chakra , Canyu Chen , Cody Coleman , Zacharie Delpierre Coudert , Leon Derczynski , Debojyoti Dutta , Ian Eisenberg , James Ezick , Heather Frase , Brian Fuller , Ram Gandikota , Agasthya Gangavarapu , Ananya Gangavarapu , James Gealy , Rajat Ghosh , James Goel , Usman Gohar , Sujata Goswami , Scott A. Hale , Wiebke Hutiri , Joseph Marvin Imperial , Surgan Jandial , Nick Judd , Felix Juefei-Xu , Foutse Khomh , Bhavya Kailkhura , Hannah Rose Kirk , Kevin Klyman , Chris Knotz , Michael Kuchnik , Shachi H. Kumar , Srijan Kumar , Chris Lengerich , Bo Li , Zeyi Liao , Eileen Peters Long , Victor Lu , Sarah Luger , Yifan Mai , Priyanka Mary Mammen , Kelvin Manyeki , Sean McGregor , Virendra Mehta , Shafee Mohammed , Emanuel Moss , Lama Nachman , Dinesh Jinenhally Naganna , Amin Nikanjam , Besmira Nushi , Luis Oala , Iftach Orr , Alicia Parrish , Cigdem Patlak , William Pietri , Forough Poursabzi-Sangdeh , Eleonora Presani , Fabrizio Puletti , Paul Röttger , Saurav Sahay , Tim Santos , Nino Scherrer , Alice Schoenauer Sebag , Patrick Schramowski , Abolfazl Shahbazi , Vin Sharma , Xudong Shen , Vamsi Sistla , Leonard Tang , Davide Testuggine , Vithursan Thangarasa , Elizabeth Anne Watkins , Rebecca Weiss , Chris Welty , Tyler Wilbers , Adina Williams , Carole-Jean Wu , Poonam Yadav , Xianjun Yang , Yi Zeng , Wenhui Zhang , Fedor Zhdanov , Jiacheng Zhu , Percy Liang , Peter Mattson , Joaquin Vanschoren

Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…

Multiagent Systems · Computer Science 2026-04-28 Juan A. Wibowo , George C. Polyzos

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…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

Cryptography and Security · Computer Science 2026-05-13 Yassin H. Rassul , Tarik A. Rashid

Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no…

Cryptography and Security · Computer Science 2026-03-17 Yi Liu , Zhihao Chen , Yanjun Zhang , Gelei Deng , Yuekang Li , Jianting Ning , Ying Zhang , Leo Yu Zhang

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we…

Artificial Intelligence · Computer Science 2026-03-13 Aniketh Garikaparthi , Manasi Patwardhan , Arman Cohan

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in…

Cryptography and Security · Computer Science 2026-02-03 Alsharif Abuadbba , Nazatul Sultan , Surya Nepal , Sanjay Jha

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

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

The prevailing paradigm in AI for physical systems (scaling general-purpose foundation models toward universal multimodal reasoning) confronts a fundamental barrier at the control interface. Recent benchmarks show that even frontier…

Artificial Intelligence · Computer Science 2026-05-21 Yoon Pyo Lee , Samrendra Roy , Jay Yoo , Kazuma Kobayashi , Sajedul Talukder , Seid Koric , Souvik Chakraborty , Syed Bahauddin Alam

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities…

Cryptography and Security · Computer Science 2026-05-12 Ziwen Cai , Yihe Zhang , Xiali Hei

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…

Artificial Intelligence · Computer Science 2026-02-09 Yichen Wu , Qianqian Gao , Xudong Pan , Geng Hong , Min Yang

AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute…

Cryptography and Security · Computer Science 2024-11-26 Edoardo Debenedetti , Jie Zhang , Mislav Balunović , Luca Beurer-Kellner , Marc Fischer , Florian Tramèr

Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents capable of perceiving, reasoning, and acting in dynamic, open-ended environments. These large-model agents mark a paradigm shift from static…

Artificial Intelligence · Computer Science 2025-07-01 Hang Su , Jun Luo , Chang Liu , Xiao Yang , Yichi Zhang , Yinpeng Dong , Jun Zhu

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

Cryptography and Security · Computer Science 2026-05-19 Sahar Abdelnabi , Eugene Bagdasarian

The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…

Cryptography and Security · Computer Science 2025-12-30 Toqeer Ali Syed , Mohammad Riyaz Belgaum , Salman Jan , Asadullah Abdullah Khan , Saad Said Alqahtani

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

Human-Computer Interaction · Computer Science 2026-02-25 Xinfeng Li , Shenyu Dai , Kelong Zheng , Yue Xiao , Gelei Deng , Wei Dong , Xiaofeng Wang
‹ Prev 1 8 9 10 Next ›