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 |
|---|---|---|---|---|---|
| Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems Jiawei Du, Jiuan Zhou, Yi Xie, Yu Cheng Published: 2026-06-13Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-13 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (99%) | - |
| Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment Jiawen Zhang, Lipeng He, N. Asokan, Yihan Wang Published: 2026-06-13Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-06-13 | cs.CR | ai-safety, alignment-training, cscr, preprint | E8 / R4 (97%) | - |
| Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure Deying Yu, Jun He Published: 2026-06-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-10 | cs.CR | ai-safety, cscr, preprint | E8 / R9 (89%) | - |
| Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs Amin Nikanjam, Arghavan Moradi Dakhel, Foutse Khomh, Kawser Wazed Nafi Published: 2026-06-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-09 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (93%) | - |
| Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops Aditi Raghunathan, Ivan Bercovich, Ivgeni Segal, Kexun Zhang Published: 2026-06-08Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-06-08 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E8 / R10 (94%) | - |
| From Privacy to Workflow Integrity: Communication-Graph Metadata in Autonomous Agent Interoperability Bijaya Dangol Published: 2026-06-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-05 | cs.CR | ai-safety, cscr, preprint | E19 / R17 (89%) | - |
| ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense Anlan Zheng, Tiantian Zhu Published: 2026-06-04Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-06-04 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E13 / R12 (93%) | - |
| SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation Aldehir Rojas, Andrew Hamara, Dwight Horne, Lawrence Wong Published: 2026-06-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-03 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (95%) | - |
| FORGE: Multi-Agent Graduated Exploitation and Detection Engineering Farooq Shaikh Published: 2026-06-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-06-02 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (95%) | - |
| Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems Chenxi Wang, Jiayan Sun, Lei Wei, Ruiyang Huang Published: 2026-05-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-27 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | - |
| The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems Benjamin Arnav, Lennart Haas, Nikolay Radev, Pablo Bernabeu-P茅rez Published: 2026-05-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-27 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (95%) | - |
| Control Physiology: An Agent-Based Model of FAIR-CAM Dynamics Jack Jones, Laura Voicu Published: 2026-05-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-26 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (95%) | - |
| Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS Bingyu Yan, Chaozhuo Li, Jinyu Hou, Litian Zhang Published: 2026-05-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-25 | cs.CR | ai-safety, cscr, preprint | E16 / R17 (94%) | - |
| KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition Kolawole Quadri Published: 2026-05-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-25 | cs.CR | ai-safety, cscr, preprint | E15 / R10 (93%) | - |
| AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Systems Petar Radanliev Published: 2026-05-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-23 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (90%) | - |
| Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms Saurabh Deochake Published: 2026-05-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-20 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | - |
| Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks Ravi Kiran Kadaboina Published: 2026-05-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-19 | cs.CR | ai-safety, cscr, preprint | E13 / R14 (94%) | - |
| Who Owns This Agent? Tracing AI Agents Back to Their Owners Alina Oprea, Doron Jonathan Ben Chayim, Eyal Lenga, Gilad Gressel Published: 2026-05-15Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-15 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (94%) | - |
| Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries Alina Oprea, Cristina Nita-Rotaru, Matthew D. Laws Published: 2026-05-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-12 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (92%) | - |
| Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents Partha Madhira Published: 2026-05-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-12 | cs.CR | ai-safety, cscr, preprint | E6 / R6 (89%) | - |
| SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces An Wang, Biaojie Zeng, Chang Jin, Chao Yang Published: 2026-05-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-12 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | - |
| HBEE: Human Behavioral Entropy Engine -- Pre-Registered Multi-Agent LLM Simulation of Peer-Suspicion-Based Detection Inversion Vickson Ferrel Published: 2026-05-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-08 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (95%) | - |
| Architectural Obsolescence of Unhardened Agentic-AI Runtimes Alfredo Metere Published: 2026-05-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-03 | cs.CR | ai-safety, cscr, preprint | E16 / R27 (95%) | - |
| Skills as Verifiable Artifacts: A Trust Schema and a Biconditional Correctness Criterion for Human-in-the-Loop Agent Runtimes Alfredo Metere Published: 2026-05-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-01 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (88%) | - |
| When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems Guangtao Zheng, Hanjie Chen, Lingxi Zhang Published: 2026-05-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-05-01 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (92%) | - |
| Compliance-Aware Agentic Payments on Stablecoin Rails Kenneth See, Xue Wen Tan Published: 2026-04-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-30 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (86%) | - |
| Ambient Persuasion in a Deployed AI Agent: Unauthorized Escalation Following Routine Non-Adversarial Content Exposure Abdoul-Aziz Maiga, Diego F. Cuadros Published: 2026-04-29Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-04-29 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E6 / R6 (90%) | - |
| Agentic Witnessing: Pragmatic and Scalable TEE-Enabled Privacy-Preserving Auditing Antony Rowstron Published: 2026-04-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-27 | cs.CR | ai-safety, cscr, preprint | E8 / R5 (97%) | - |
| AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents Jiaqing Wu, Ke Xu, Qi Li, Xinhao Deng Published: 2026-04-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-27 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (98%) | - |
| Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing Kaisheng Fan, Tegawend茅 F. Bissyand茅, Weizhe Zhang, Xunzhu Tang Published: 2026-04-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-27 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (96%) | - |