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 |
|---|---|---|---|---|---|
| CivicShield: A Cross-Domain Defense-in-Depth Framework for Securing Government-Facing AI Chatbots Against Multi-Turn Adversarial Attacks KrishnaSaiReddy Patil Published: 2026-03-30Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-30 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Design Principles for the Construction of a Benchmark Evaluating Security Operation Capabilities of Multi-agent AI Systems Guodong Dong, Mitchell John DeStefano, Peiyu Tseng, Peng Liu Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Evaluating Privilege Usage of Agents on Real-World Tools Chijin Zhou, Geguang Pu, Gwihwan Go, Lianhang Fu Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (95%) | - |
| FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation Rong Pan, Ruiyang Wang, Zhengan Yao Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (94%) | - |
| GMA-SAWGAN-GP: A Novel Data Generative Framework to Enhance IDS Detection Performance Safak Dogan, Xiyu Shi, Ziyu Mu Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (96%) | - |
| Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers Haochuan Kevin Wang Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (95%) | - |
| Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing Alessio Langiu Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (93%) | - |
| Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning Alwin Peng, Bilgehan Sel, Jerry Wei, Ming Jin Published: 2026-03-30Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-30 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| "What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents Mingchen Li, Zifan Peng Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (98%) | - |
| "What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents Zifan Peng Published: 2026-03-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-30 | cs.CR | ai-safety, cscr, preprint | E4 / R2 (96%) | - |
| A Systematic Taxonomy of Security Vulnerabilities in the OpenClaw AI Agent Framework Guofei Gu, Surada Suwansathit, Yuxuan Zhang Published: 2026-03-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-29 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation Dongyi Lv, He Yang, Jizhong Zhao, Song Ma Published: 2026-03-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-29 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Gender-Based Heterogeneity in Youth Privacy-Protective Behavior for Smart Voice Assistants: Evidence from Multigroup PLS-SEM Ajay Kumar Shrestha, Molly Campbell, Yulia Bobkova Published: 2026-03-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-28 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (95%) | - |
| GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models Joaquin Molto, Md Jueal Mia, M. Hadi Amini, Yanzhao Wu Published: 2026-03-28Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-28 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do Aditya Dhodapkar, Farhaan Pishori Published: 2026-03-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-28 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| SkillTester: Benchmarking Utility and Security of Agent Skills Anjie Xu, Leye Wang, Zixing Wang Published: 2026-03-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-28 | cs.CR | ai-safety, cscr, preprint | E4 / R2 (95%) | - |
| Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models Matthew Canabarro, Praneel Panchigar, Torlach Rush Published: 2026-03-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-28 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Clawed and Dangerous: Can We Trust Open Agentic Systems? Guangsheng Yu, Liming Zhu, Qin Wang, Shiping Chen Published: 2026-03-27Area: cs.CRCitations: 50 Tags: ai-safety, cscr, preprint | 2026-03-27 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | 50 |
| Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization Chong Wang, Pan Li, Shaohua Li, Wanxu Xia Published: 2026-03-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-27 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (94%) | - |
| Machine Learning Transferability for Malware Detection C茅sar Vieira, Eva Maia, Isabel Pra莽a, Jo茫o Vitorino Published: 2026-03-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-27 | cs.CR | ai-safety, cscr, preprint | E9 / R3 (95%) | - |
| CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks Abdullah Al Noman, Md Arifur Rahman, Md. Rokon Mia, Prodip Kumar Sarker Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| Design and Development of an ML/DL Attack Resistance of RC-Based PUF for IoT Security Joy Acharya, Mohendra Roy, Paawan Sharma, Smit Patel Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E7 / R3 (95%) | - |
| PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems Haoyue Liu, Haozhen Wang, Jionghao Zhu, Xiaoying Tang Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models Eyal Hadad, Mordechai Guri Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models Eyal Hadad, Mordechai Guri Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (95%) | - |
| Sovereign AI at the Front Door of Care: A Physically Unidirectional Architecture for Secure Clinical Intelligence Dhriti Vasu, Vasu Srinivasan Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (93%) | - |
| TAAC: A gate into Trustable Audio Affective Computing Feng-Qi Cui, Xintao Hu Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (97%) | - |
| The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities Ron Litvak Published: 2026-03-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-26 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| AIP: Agent Identity Protocol for Verifiable Delegation Across MCP and A2A Sunil Prakash Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (96%) | - |
| AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective Siyu Luan, Zhenyi Wang Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (97%) | - |