English
Related papers

Related papers: Aligning Provenance with Authorization: A Dual-Gra…

200 papers

Large Language Models (LLMs) have been equipped with safety mechanisms to prevent harmful outputs, but these guardrails can often be bypassed through "jailbreak" prompts. This paper introduces a novel graph-based approach to systematically…

Cryptography and Security · Computer Science 2025-04-18 Sinan He , An Wang

Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…

Computation and Language · Computer Science 2025-06-02 Qianqian Zhang , Jiajia Liao , Heting Ying , Yibo Ma , Haozhan Shen , Jingcheng Li , Peng Liu , Lu Zhang , Chunxin Fang , Kyusong Lee , Ruochen Xu , Tiancheng Zhao

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

Artificial Intelligence · Computer Science 2025-07-14 Zeyang Sha , Hanling Tian , Zhuoer Xu , Shiwen Cui , Changhua Meng , Weiqiang Wang

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Multiagent Systems · Computer Science 2026-04-21 Nokimul Hasan Arif , Qian Lou , Mengxin Zheng

We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…

Machine Learning · Computer Science 2024-08-07 Hannah Brown , Leon Lin , Kenji Kawaguchi , Michael Shieh

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

Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions…

Artificial Intelligence · Computer Science 2026-04-13 Hongyin Zhu , Jinming Liang , Mengjun Hou , Ruifan Tang , Xianbin Zhu , Jingyuan Yang , Yuanman Mao , Feng Wu

Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM agents is to better…

Computation and Language · Computer Science 2025-11-12 Siyu Xia , Zekun Xu , Jiajun Chai , Wentian Fan , Yan Song , Xiaohan Wang , Guojun Yin , Wei Lin , Haifeng Zhang , Jun Wang

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms…

Computation and Language · Computer Science 2026-05-29 Aditya Nawal , Manit Baser , Mohan Gurusamy

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, current defenses are…

Cryptography and Security · Computer Science 2025-10-13 Debeshee Das , Luca Beurer-Kellner , Marc Fischer , Maximilian Baader

We address a problem of area protection in graph-based scenarios with multiple agents. The problem consists of two adversarial teams of agents that move in an undirected graph shared by both teams. Agents are placed in vertices of the…

Artificial Intelligence · Computer Science 2017-08-25 Marika Ivanová , Pavel Surynek

The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic…

Multiagent Systems · Computer Science 2025-10-21 Xinfeng Li , Dong Huang , Jie Li , Hongyi Cai , Zhenhong Zhou , Wei Dong , XiaoFeng Wang , Yang Liu

Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications. In this work, we focus on the…

Machine Learning · Computer Science 2022-11-16 Zhihao Zhu , Chenwang Wu , Min Zhou , Hao Liao , Defu Lian , Enhong Chen

Retrieval Augmented Generation (RAG) is a technique commonly used to equip models with out of distribution knowledge. This process involves collecting, indexing, retrieving, and providing information to an LLM for generating responses.…

Cryptography and Security · Computer Science 2024-08-13 Gianluca De Stefano , Lea Schönherr , Giancarlo Pellegrino

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

Graph Retrieval Augmented Generation (GraphRAG) effectively enhances external knowledge integration capabilities by explicitly modeling knowledge relationships, thereby improving the factual accuracy and generation quality of Large Language…

Artificial Intelligence · Computer Science 2025-06-05 Junqi Gao , Xiang Zou , YIng Ai , Dong Li , Yichen Niu , Biqing Qi , Jianxing Liu

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Artificial Intelligence · Computer Science 2026-01-08 Kanghua Mo , Li Hu , Yucheng Long , Zhihao Li

Advanced Persistent Threats (APTs) represent sophisticated cyberattacks characterized by their ability to remain undetected within the victim system for extended periods, aiming to exfiltrate sensitive data or disrupt operations. Existing…

Cryptography and Security · Computer Science 2025-07-18 Wei Qiao , Yebo Feng , Teng Li , Zhuo Ma , Yulong Shen , JianFeng Ma , Yang Liu

Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-based retrieval to improve factual grounding. Recent…

Artificial Intelligence · Computer Science 2026-04-16 Yuchen Ying , Weiqi Jiang , Tongya Zheng , Yu Wang , Shunyu Liu , Kaixuan Chen , Mingli Song
‹ Prev 1 8 9 10 Next ›