English
Related papers

Related papers: Governance Architecture for Autonomous Agent Syste…

200 papers

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

Cryptography and Security · Computer Science 2026-02-27 Qianlong Lan , Anuj Kaul , Shaun Jones , Stephanie Westrum

This paper introduces LUCID-MA (Learning and Understanding Crime through Dialogue of Multiple Agents), an innovative AI powered framework where multiple AI agents collaboratively analyze and understand crime data. Our system that consists…

Multiagent Systems · Computer Science 2025-07-22 Syeda Kisaa Fatima , Tehreem Zubair , Noman Ahmed , Asifullah Khan

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions.…

Cryptography and Security · Computer Science 2026-05-26 Ariel Fogel , Omer Hofman , Eilon Cohen , Roman Vainshtein

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Cryptography and Security · Computer Science 2025-02-17 Jizhou Chen , Samuel Lee Cong

Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cost…

Computation and Language · Computer Science 2026-04-22 Abdullah Mohammad , Sushant Kumar Ray , Pushkar Arora , Rafiq Ali , Ebad Shabbir , Gautam Siddharth Kashyap , Jiechao Gao , Usman Naseem

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

Machine Learning · Computer Science 2025-10-08 Zizhao Wang , Dingcheng Li , Vaishakh Keshava , Phillip Wallis , Ananth Balashankar , Peter Stone , Lukas Rutishauser

The proliferation of autonomous AI agents within enterprise environments introduces a critical security challenge: managing access control for emergent, novel tasks for which no predefined policies exist. This paper introduces an advanced…

Cryptography and Security · Computer Science 2025-10-14 Charles Fleming , Ashish Kundu , Ramana Kompella

Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or…

Cryptography and Security · Computer Science 2026-05-19 Nanxi Li , Zhengyue Zhao , Chaowei Xiao

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Cryptography and Security · Computer Science 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…

Artificial Intelligence · Computer Science 2026-04-28 Rong Xiang

Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under adversarial prompting. Existing safety approaches -- such as reinforcement learning from human…

Artificial Intelligence · Computer Science 2026-03-20 Zou Qiang

Prompt injection attacks, where untrusted data contains an injected prompt to manipulate the system, have been listed as the top security threat to LLM-integrated applications. Model-level prompt injection defenses have shown strong…

Cryptography and Security · Computer Science 2026-02-09 Sizhe Chen , Arman Zharmagambetov , David Wagner , Chuan Guo

Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…

Artificial Intelligence · Computer Science 2025-11-12 Alejandro R. Jadad

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

Cryptography and Security · Computer Science 2025-02-19 Tvrtko Sternak , Davor Runje , Dorian Granoša , Chi Wang

Prompt injection constitutes a significant challenge for generative AI systems by inducing unintended outputs. We introduce a multi-agent NLP framework specifically designed to address prompt injection vulnerabilities through layered…

Artificial Intelligence · Computer Science 2025-03-17 Diego Gosmar , Deborah A. Dahl , Dario Gosmar

Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generating harmful content and are vulnerable to jailbreaking…

Cryptography and Security · Computer Science 2026-04-21 Zeming Wei , Chengcan Wu , Meng Sun

The rapid advancement of Large Language Model (LLM)-driven multi-agent systems has significantly streamlined software developing tasks, enabling users with little technical expertise to develop executable applications. While these systems…

Cryptography and Security · Computer Science 2025-11-25 Xiaoqing Wang , Keman Huang , Bin Liang , Hongyu Li , Xiaoyong Du

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300…

Artificial Intelligence · Computer Science 2026-04-21 Bhaskar Gurram

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

Cryptography and Security · Computer Science 2026-05-27 Faruk Alpay , Taylan Alpay

We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes fifteen failure-detection tools and two root-cause analysis…

Artificial Intelligence · Computer Science 2026-04-01 Hadar Mulian , Sergey Zeltyn , Ido Levy , Liane Galanti , Avi Yaeli , Segev Shlomov
‹ Prev 1 3 4 5 6 7 10 Next ›