English
Related papers

Related papers: Sealing the Audit-Runtime Gap for LLM Skills

200 papers

Large Language Models (LLMs) have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety alignments. Guardrails--external defense mechanisms that…

Cryptography and Security · Computer Science 2025-10-17 Xunguang Wang , Zhenlan Ji , Wenxuan Wang , Zongjie Li , Daoyuan Wu , Shuai Wang

Security code review is a time-consuming and labor-intensive process typically requiring integration with automated security defect detection tools. However, existing security analysis tools struggle with poor generalization, high false…

Software Engineering · Computer Science 2026-05-12 Jiaxin Yu , Peng Liang , Yujia Fu , Amjed Tahir , Mojtaba Shahin , Chong Wang , Yangxiao Cai

Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…

In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls…

Cryptography and Security · Computer Science 2025-05-19 Jia Hui Chin , Pu Zhang , Yu Xin Cheong , Jonathan Pan

Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs often contain subtle but critical vulnerabilities, posing significant risks when deployed…

Computation and Language · Computer Science 2025-10-14 Alexander Sternfeld , Andrei Kucharavy , Ljiljana Dolamic

The integration of Large Language Models (LLMs) into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities…

Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps…

Artificial Intelligence · Computer Science 2026-04-21 Sampriti Saha , Pranav Hemanth

Large Language Models (LLMs) have become powerful tools for automated code generation. However, these models often overlook critical security practices, which can result in the generation of insecure code that contains…

Software Engineering · Computer Science 2025-07-01 Hao Yan , Swapneel Suhas Vaidya , Xiaokuan Zhang , Ziyu Yao

We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…

Computation and Language · Computer Science 2025-05-13 Weiliang Zhao , Daniel Ben-Levi , Wei Hao , Junfeng Yang , Chengzhi Mao

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…

Cryptography and Security · Computer Science 2025-07-28 Gabriel Chua

Large language models (LLMs) are increasingly used as semantic encoders and decoders in semantic communication. However, current LLM based systems mostly remain monolithic: a single prompted model, or a tightly coupled transmitter/receiver…

Systems and Control · Electrical Eng. & Systems 2026-05-05 Jingwen Fu , Ming Xiao , Mikael Skoglund

Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes SafeGPT, a…

Cryptography and Security · Computer Science 2026-05-26 Pratyush Desai , Luoxi Tang , Yuqiao Meng , Zhaohan Xi

Code security and usability are both essential for various coding assistant applications driven by large language models (LLMs). Current code security benchmarks focus solely on single evaluation task and paradigm, such as code completion…

Computation and Language · Computer Science 2025-05-16 Yutao Mou , Xiao Deng , Yuxiao Luo , Shikun Zhang , Wei Ye

The Large Language Models (LLM) are increasingly being deployed in robotics to generate robot control programs for specific user tasks, enabling embodied intelligence. Existing methods primarily focus on LLM training and prompt design that…

Robotics · Computer Science 2025-08-27 ZhenDong Chen , ZhanShang Nie , ShiXing Wan , JunYi Li , YongTian Cheng , Shuai Zhao

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

Computation and Language · Computer Science 2026-04-10 Devang Kulshreshtha , Hang Su , Haibo Jin , Chinmay Hegde , Haohan Wang

The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged as a cost-effective solution, allowing individuals and small companies to…

Machine Learning · Computer Science 2026-02-03 Yifan Sun , Yuhang Li , Yue Zhang , Yuchen Jin , Huan Zhang

As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust between processing stages become a practical concern. This paper presents a…

Cryptography and Security · Computer Science 2025-11-03 Dominik Schwarz

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…

Software Engineering · Computer Science 2025-08-19 Satyam Kumar Navneet , Joydeep Chandra

Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a…

Artificial Intelligence · Computer Science 2026-05-18 Duling Xu , Zheng Chen , Zaifeng Pan , Jiawei Guan , Dong Dong , Jialin Li , Bangzheng Pu

Enterprise penetration-testing is often limited by high operational costs and the scarcity of human expertise. This paper investigates the feasibility and effectiveness of using Large Language Model (LLM)-driven autonomous systems to…

Cryptography and Security · Computer Science 2025-09-12 Andreas Happe , Jürgen Cito