English
Related papers

Related papers: "Elementary, My Dear Watson." Detecting Malicious …

200 papers

LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that these systems can hallucinate non-existent package names, which…

Cryptography and Security · Computer Science 2026-05-12 Yiyong Liu , Chia-Yi Hsu , Chun-Ying Huang , Michael Backes , Rui Wen , Chia-Mu Yu

Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications.…

Cryptography and Security · Computer Science 2026-03-18 Florian Holzbauer , David Schmidt , Gabriel Gegenhuber , Sebastian Schrittwieser , Johanna Ullrich

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

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on…

Cryptography and Security · Computer Science 2026-04-20 Yukun Jiang , Yage Zhang , Michael Backes , Xinyue Shen , Yang Zhang

Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…

Computation and Language · Computer Science 2026-05-05 Qiliang Liang , Hansi Wang , Zhong Liang , Yang Liu

This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and…

Robotics · Computer Science 2026-03-03 Hakan Aktas , Yigit Yildirim , Ahmet Firat Gamsiz , Deniz Bilge Akkoc , Erhan Oztop , Emre Ugur

Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge…

Machine Learning · Computer Science 2026-03-24 Abed K. Musaffar , Ambuj Singh , Francesco Bullo

Large language models (LLMs) have facilitated the generation of high-quality, cost-effective synthetic data for developing downstream models and conducting statistical analyses in various domains. However, the increased reliance on…

Machine Learning · Computer Science 2025-02-04 Yixin Wu , Ziqing Yang , Yun Shen , Michael Backes , Yang Zhang

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

Artificial Intelligence · Computer Science 2025-12-30 Sadia Asif , Israel Antonio Rosales Laguan , Haris Khan , Shumaila Asif , Muneeb Asif

A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning. In this article, we delve into the performance of Large Language Models (LLMs) in dealing…

Artificial Intelligence · Computer Science 2023-09-13 Thilini Wijesiriwardene , Amit Sheth , Valerie L. Shalin , Amitava Das

The detection and grounding of multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation. While existing methods have made progress in recent years, we identify two fundamental limitations in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Yuchen Zhang , Yaxiong Wang , Yujiao Wu , Lianwei Wu , Li Zhu , Zhedong Zheng

Malicious package detection has become a critical task in ensuring the security and stability of the PyPI. Existing detection approaches have focused on advancing model selection, evolving from traditional machine learning (ML) models to…

Cryptography and Security · Computer Science 2025-06-18 Xingan Gao , Xiaobing Sun , Sicong Cao , Kaifeng Huang , Di Wu , Xiaolei Liu , Xingwei Lin , Yang Xiang

Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong reasoning capabilities is regarded as a crucial milestone in…

Artificial Intelligence · Computer Science 2025-08-20 Xiao-Wen Yang , Jie-Jing Shao , Lan-Zhe Guo , Bo-Wen Zhang , Zhi Zhou , Lin-Han Jia , Wang-Zhou Dai , Yu-Feng Li

Despite their linguistic competence, Large Language Models (LLMs) often struggle to reason reliably and flexibly. To identify these shortcomings, we introduce the Non-Linear Reasoning (NLR) dataset, a collection of 55 unique, hand-designed…

Computation and Language · Computer Science 2025-12-02 Nasim Borazjanizadeh , Steven T. Piantadosi

Modern cybersecurity requires systematic ways to evaluate how detection systems respond to evolving and previously unseen attack behaviors. Existing malware repositories largely capture known patterns and provide limited support for…

Cryptography and Security · Computer Science 2026-05-01 Bikash Saha , Sandeep Kumar Shukla

Supply chain networks are complex systems that are challenging to analyze; this problem is exacerbated when there are illicit activities involved in the supply chain, such as counterfeit parts, forced labor, or human trafficking. While…

Artificial Intelligence · Computer Science 2025-07-11 Zili Wang , Frank Montabon , Kristin Yvonne Rozier

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…

Computation and Language · Computer Science 2026-04-16 Haichuan Hu , Ye Shang , Quanjun Zhang

As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, LLM-as-a-Judge, faces a fundamental dilemma: how can…

Artificial Intelligence · Computer Science 2026-02-13 Jiayi Zhou , Yang Sheng , Hantao Lou , Yaodong Yang , Jie Fu

In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and…

Cryptography and Security · Computer Science 2026-05-12 Yuepeng Hu , Yuqi Jia , Mengyuan Li , Dawn Song , Neil Gong

In recent years, neuro-symbolic methods have become a popular and powerful approach that augments artificial intelligence systems with the capability to perform abstract, logical, and quantitative deductions with enhanced precision and…

Artificial Intelligence · Computer Science 2025-02-04 Yuxuan Wu , Hideki Nakayama
‹ Prev 1 2 3 10 Next ›