Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems Chengcan Wu, Haolin Wu, Huanran Chen, Jiangrong Wu Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents Aur茅lien Francillon, Daniele Perito, Merve Sahin, Simone Aonzo Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (92%) | - |
| How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition Andy Zou, Arman Zharmagambetov, Benjamin L. Edelman, Eliot Jones Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration Bin Wu, Guangquan Xu, Qiannan Si, Tiejun Wu Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-03-16 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E4 / R3 (94%) | - |
| TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems Biaojie Zeng, Chang Jin, Chao Yang, Hefeng Zhou Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (98%) | - |
| Adversarial attacks against Modern Vision-Language Models Alejandro Paredes La Torre Published: 2026-03-17Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-17 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E6 / R3 (95%) | - |
| Deep learning based intelligent IDS for Large-scale IoT networks Isha Andrade, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E30 / R23 (95%) | - |
| DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns Thomas Bauschert, Tri Gia Nguyen, Trung V. Phan Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (98%) | - |
| Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning Shan Jin, Shenao Yan, Shimaa Ahmed, Sunpreet S. Arora Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models Isha Andrade, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence Adrian Taylor, Alex Popa, Ranwa Al Mallah Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E32 / R18 (94%) | - |
| Malicious Or Not: Adding Repository Context to Agent Skill Classification David Schmidt, Florian Holzbauer, Gabriel Gegenhuber, Johanna Ullrich Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (95%) | - |
| PAuth - Precise Task-Scoped Authorization For Agents Linxi Jiang, Reshabh K Sharma, Shuo Chen, Zhiqiang Lin Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (98%) | - |
| Resource Consumption Threats in Large Language Models Kun Wang, Li Sun, Sen Su, Weiliu Wang Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (93%) | - |
| Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework Iman Vakilinia, Taiwo Onitiju Published: 2026-03-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-17 | cs.CR | ai-safety, cscr, preprint | E6 / R2 (95%) | - |
| Towards Unsupervised Adversarial Document Detection in Retrieval Augmented Generation Systems Patrick Levi Published: 2026-03-17Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-17 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare Saikat Maiti Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs Quanyan Zhu, Ya-Ting Yang Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Machine Learning for Network Attacks Classification and Statistical Evaluation of Machine Learning for Network Attacks Classification and Adversarial Learning Methodologies for Synthetic Data Generation Christos Douligeris, Iakovos-Christos Zarkadis Published: 2026-03-18Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint, safety-evaluation | 2026-03-18 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint, safety-evaluation | E5 / R3 (97%) | - |
| MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0) Alex Leung, Kentaroh Toyoda, Yi Ting Shen Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (98%) | - |
| Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards Andreas Happe, Daniel Arp, J眉rgen Cito, Philipp Normann Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (98%) | - |
| Retrieval-Augmented LLMs for Security Incident Analysis Aditya Vikram Singh, Alex Fitts, Alina Oprea, Dirk Van Bruggen Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (93%) | - |
| Retrieval-Augmented LLMs for Security Incident Analysis Aditya Vikram Singh, Alex Fitts, Alina Oprea, Dirk Van Bruggen Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| WebPII: Benchmarking Visual PII Detection for Computer-Use Agents Nathan Zhao Published: 2026-03-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-18 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (98%) | - |
| A Framework for Formalizing LLM Agent Security Chenguang Wang, Dawn Song, Jingxuan He, Kyle Montgomery Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (96%) | - |
| Agent Control Protocol: Admission Control for Agent Actions Marcelo Fernandez Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (95%) | - |
| Agent Control Protocol: Admission Control for Agent Actions Marcelo Fernandez Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (96%) | - |
| Agent Control Protocol: Admission Control for Agent Actions Marcelo Fernandez Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E39 / R36 (98%) | - |
| Agent Control Protocol: Admission Control for Agent Actions Marcelo Fernandez Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (98%) | - |
| A Novel Solution for Zero-Day Attack Detection in IDS using Self-Attention and Jensen-Shannon Divergence in WGAN-GP Safak Dogan, Xiyu Shi, Ziyu Mu Published: 2026-03-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-19 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |