English
Related papers

Related papers: The Granularity Mismatch in Agent Security: Argume…

200 papers

Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…

Artificial Intelligence · Computer Science 2025-08-01 Haoyu Wang , Christopher M. Poskitt , Jun Sun

Analytic software tools and workflows are increasing in capability, complexity, number, and scale, and the integrity of our workflows is as important as ever. Specifically, we must be able to inspect the process of analytic workflows to…

Artificial Intelligence · Computer Science 2020-11-10 Scott Friedman , Jeff Rye , David LaVergne , Dan Thomsen , Matthew Allen , Kyle Tunis

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

LLM agents increasingly act on external systems, yet tool effects are immediate. Under failures, speculation, or contention, losing branches can leak unintended side effects with no safe rollback. We introduce Atomix, a runtime that…

Machine Learning · Computer Science 2026-02-17 Bardia Mohammadi , Nearchos Potamitis , Lars Klein , Akhil Arora , Laurent Bindschaedler

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

Artificial Intelligence · Computer Science 2026-01-26 Donghao Huang , Gauri Malwe , Zhaoxia Wang

Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM-generated texts. This increases the risk of misuse and highlights the need for reliable…

Machine Learning · Computer Science 2025-11-19 Zheng Chen , Yushi Feng , Jisheng Dang , Yue Deng , Changyang He , Hongxi Pu , Haoxuan Li , Bo Li

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Computation and Language · Computer Science 2025-11-18 Dongyoon Hahm , Taywon Min , Woogyeol Jin , Kimin Lee

Web-use agents are rapidly being deployed to automate complex web tasks with extensive browser capabilities. However, these capabilities create a critical and previously unexplored attack surface. This paper demonstrates how attackers can…

Cryptography and Security · Computer Science 2025-10-22 Avishag Shapira , Parth Atulbhai Gandhi , Edan Habler , Asaf Shabtai

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Cryptography and Security · Computer Science 2024-01-03 Daniel Wankit Yip , Aysan Esmradi , Chun Fai Chan

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Artificial Intelligence · Computer Science 2026-03-13 Yonas Atinafu , Robin Cohen

An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half…

Cryptography and Security · Computer Science 2026-05-04 Hongbo Wen , Ying Li , Hanzhi Liu , Chaofan Shou , Yanju Chen , Yuan Tian , Yu Feng

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…

Machine Learning · Computer Science 2025-10-23 Hwiwon Lee , Ziqi Zhang , Hanxiao Lu , Lingming Zhang

Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, large language models (LLMs) with strong common sense knowledge have emerged in the domain of ITD. Nevertheless, diverse activity…

Cryptography and Security · Computer Science 2024-08-20 Chengyu Song , Linru Ma , Jianming Zheng , Jinzhi Liao , Hongyu Kuang , Lin Yang

Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production. Recent large language models can accelerate this work, and recent benchmarks…

Logic in Computer Science · Computer Science 2026-05-28 Leo Yao

Agents are LLM-driven components that can mutate environments in powerful, arbitrary ways. Extracting guarantees for the execution of agents in production environments can be challenging due to asynchrony and failures. In this paper, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-10 Mahesh Balakrishnan , Ashwin Bharambe , Davide Testuggine , David Geraghty , David Mao , Vidhya Venkat , Ilya Mironov , Rithesh Baradi , Gayathri Aiyer , Victoria Dudin

Advanced cyber threats (e.g., Fileless Malware and Advanced Persistent Threat (APT)) have driven the adoption of provenance-based security solutions. These solutions employ Machine Learning (ML) models for behavioral modeling and critical…

Cryptography and Security · Computer Science 2025-10-10 Kunal Mukherjee , Joshua Wiedemeier , Tianhao Wang , Muhyun Kim , Feng Chen , Murat Kantarcioglu , Kangkook Jee

Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to produce triage labels, incident summaries, or remediation advice. We study a structural…

Cryptography and Security · Computer Science 2026-05-26 Rohan Pandey , Archit Bhujang

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Cryptography and Security · Computer Science 2026-03-30 Shiping Chen , Qin Wang , Guangsheng Yu , Xu Wang , Liming Zhu

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuexin Li , Yue Liu , Yangqiu Song , Bryan Hooi

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for…

Artificial Intelligence · Computer Science 2026-05-12 Pedro Conde , Henrique Branquinho , Valerio Mazzone , Bruno Mendes , André Baptista , Nuno Moniz