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 |
|---|---|---|---|---|---|
| Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution Jos茅 Luis Pino Published: 2026-09-24Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E15 / R9 (90%) | 22 |
| Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution Jos茅 Luis Pino Published: 2026-09-24Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (90%) | 22 |
| Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure Ameya Prabhu, Anselm Paulus, David Schmotz, Derck Prinzhorn Published: 2026-09-24Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | 15 |
| LLM Agents Can Easily Tamper With Their Own Traces Ameya Prabhu, David Schmotz, Derck Prinzhorn, Jeremy Qin Published: 2026-09-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (94%) | - |
| On the Effectiveness of Kernel-Level Evidence for Agent Security Baris Coskun, Kay Liu, Mikhail Kuznetsov, Spencer King Published: 2026-09-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (92%) | - |
| Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs Adam Ek, Luk谩拧 Br暖na, Robert Bridges Published: 2026-09-24Area: cs.CRCitations: 31 Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E12 / R10 (93%) | 31 |
| Subjects, Not Authors: The Authorship Hazard in Agentic Dataspaces Changbin Lee, Seungho Lee Published: 2026-09-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (93%) | - |
| Template Ageing and Longitudinal Verification in Fixed-Text Keystroke Dynamics: A Subject-Disjoint Study Across Eight Weeks Na Liu, Qing Xu, Saad Khan, Simon Parkinson Published: 2026-09-24Area: cs.CRCitations: 36 Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (94%) | 36 |
| The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning Aditya Nawal, Dinil Mon Divakaran, Manit Baser, Mohan Gurusamy Published: 2026-09-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E13 / R12 (88%) | - |
| TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models Eisuke Koizumi, Masao Sakai, Minoru Kuribayashi, Satoru Matsumoto Published: 2026-09-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-24 | cs.CR | ai-safety, cscr, preprint | E8 / R5 (95%) | - |
| Agent Name Collision Attacks in Multi-Agent Systems Adithyan Arun Kumar Published: 2026-09-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E12 / R11 (94%) | - |
| Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications Harsh Verma Published: 2026-09-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (88%) | - |
| Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions Tiantong Wu, Wei Yang Bryan Lim Published: 2026-09-23Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (94%) | 15 |
| Issuer-Sovereign Agentic Payments Ashu Kanaujia, Dishant Sharma, Rajneesh Kaushal Published: 2026-09-23Area: cs.CRCitations: 6 Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E13 / R10 (89%) | 6 |
| Multi-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls Hoang-Huy Nguyen-Huu, Khuong Nguyen-An, Van-Tri Phan Published: 2026-09-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-09-23 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E12 / R7 (93%) | - |
| Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents Bibo Tu, Haojun Xia, Jingkun Yue, Jinqian Zhang Published: 2026-09-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | - |
| Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents Ahmed Yehia, Mohammad Mamun, Saeedeh Lohrasbi, Scott Buffett Published: 2026-09-23Area: cs.CRCitations: 8 Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E14 / R9 (94%) | 8 |
| Who Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior Chuyi Wang, Fangchen Luo, Tongze Wang, Xiaohui Xie Published: 2026-09-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-23 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (92%) | - |
| A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem Cheng-zhong Xu, Juanjuan Zhao, Kejiang Ye, Laizhen Li Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E12 / R13 (94%) | - |
| Ajar: Measuring Open Privilege in Agent Defenses Linxi Jiang, Reshabh K Sharma, Shuo Chen, Zhiqiang Lin Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (93%) | - |
| Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection 脕lvaro Pardo, Amanda Riverol, Gustavo Betarte, Rodrigo Mart铆nez Published: 2026-09-22Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-09-22 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E7 / R7 (94%) | 22 |
| From Alignment to Access Control: A Framework for GenAI Policy Enforcement Nathalie Baracaldo Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, alignment-training, cscr, preprint | E10 / R9 (95%) | - |
| On the security and privacy of LLMs in Mobility Lorenzo Perinello, Mauro Conti, Umberto Salviati Published: 2026-09-22Area: cs.CRCitations: 35 Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (92%) | 35 |
| The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems Pengfei He, Yue Xing, Zitao Li Published: 2026-09-22Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (96%) | 12 |
| Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic Ali Melih Kanca, Ilker Turker Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E12 / R8 (94%) | - |
| Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic Ali Melih Kanca, Ilker Turker Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E12 / R7 (94%) | - |
| Toward Responsible AI-Augmented Cyber Defense: Pattern Recognition, Defense-in-Depth, and the Case for Human-AI Collaboration Hayder Kareem Abed, Mustafa S. Aljumaily, Nawar S. Alseelawi Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | - |
| When Clients Are Orchestrated: Strategic Gradient Manipulation to Defeat Federated Learning Servers with Efficient Defense Ahmed Abdelnaby, Mohamed Elmahallawy, Mohamed Shaaban Published: 2026-09-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-22 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (93%) | - |
| ActGov: Governing LLM Agent Actions via Policy-Constrained Validation Kaiyuan Zhang, Ke Jiang, Yinqian Zhang, Yuke Peng Published: 2026-09-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-21 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (91%) | - |
| ActGov: Governing LLM Agent Actions via Policy-Constrained Validation Kaiyuan Zhang, Ke Jiang, Yinqian Zhang, Yuke Peng Published: 2026-09-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-21 | cs.CR | ai-safety, cscr, preprint | - | - |