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 |
|---|---|---|---|---|---|
| Verifier-Bound Communication for LLM Agents: Certified Bounds on Covert Signaling Om Tailor Published: 2026-02-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (90%) | - |
| Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models Chung-ju Huang, Huiqiang Zhao, Leye Wang, Lijian Li Published: 2026-02-27Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | 45 |
| Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents Haotian Luo, Linxi Jiang, Zhijie Liu, Zhiqiang Lin Published: 2026-02-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-28 | cs.CR | ai-safety, cscr, preprint | E8 / R5 (92%) | - |
| Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs Jiandong Gao, Jingyuan Xie, Ji Wu, Wenjie Wang Published: 2026-02-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-28 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (90%) | - |
| TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systems Chang Xue, Chen Yang, Fang Liu, Jiaye Wang Published: 2026-02-28Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-02-28 | cs.CR | ai-safety, cscr, preprint | E13 / R7 (94%) | 22 |
| AMDS: Attack-Aware Multi-Stage Defense System for Network Intrusion Detection with Two-Stage Adaptive Weight Learning Nick Rahimi, Oluseyi Olukola Published: 2026-03-01Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (90%) | 45 |
| ATLAS: AI-Assisted Threat-to-Assertion Learning for System-on-Chip Security Verification Alexander Garcia, Ishraq Tashdid, Jonathan Valamehr, Kimia Tasnia Published: 2026-03-01Area: cs.CRCitations: 55 Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E16 / R13 (91%) | 55 |
| AWE: Adaptive Agents for Dynamic Web Penetration Testing Akshat Singh Jaswal, Ashish Baghel Published: 2026-03-01Area: cs.CRCitations: 14 Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E25 / R21 (91%) | 14 |
| Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders Alex Levinson, Bert Herring, Christina Q Knight, Dan Borges Published: 2026-03-01Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, alignment-training, cscr, preprint | E10 / R6 (91%) | - |
| Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction Hailin Yang, Heng Xu, Huajie Chen, Hui Sun Published: 2026-03-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E16 / R18 (90%) | - |
| Quantifying Frontier LLM Capabilities for Container Sandbox Escape Art O Cathain, Harry Coppock, Jason Gwartz, Jerome Wynne Published: 2026-03-01Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E9 / R6 (91%) | 45 |
| Turning Black Box into White Box: Dataset Distillation Leaks Feng He, Huajie Chen, Jialiang Shen, Lefeng Zhang Published: 2026-03-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-01 | cs.CR | ai-safety, cscr, preprint | E11 / R12 (91%) | - |
| ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code Elzo Brito dos Santos Filho Published: 2026-03-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-06 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (96%) | - |
| Supporting Artifact Evaluation with LLMs: A Study with Published Security Research Papers Anastasiia Belova, David Heye, Jan Pennekamp, Johannes Lohm枚ller Published: 2026-03-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-03-06 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E6 / R4 (93%) | - |
| aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness FaSheng Miao, Fubin Wu, Lu Sun, Xiang Li Published: 2026-03-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-07 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (93%) | - |
| Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice Yuxu Ge Published: 2026-03-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-07 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| mAVE: A Watermark for Joint Audio-Visual Generation Models Leyi Pan, Lijie Wen, Luyang Si Published: 2026-03-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-07 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (95%) | - |
| Targeted Bit-Flip Attacks on LLM-Based Agents Bingyi He, Ee-Chien Chang, Jialai Wang, Ya Wen Published: 2026-03-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-07 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs Hanxun Huang, Jun Sun, Nay Myat Min, Wei Zhao Published: 2026-03-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-08 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (99%) | - |
| DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation Bo Jiang Published: 2026-03-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-08 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents Hao Peng, Heqing Huang, Jiafei Wu, Lu Zhou Published: 2026-03-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-08 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (97%) | - |
| Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems Biwei Yan, Boyang Ma, Kaidi Xu, Minghui Xu Published: 2026-03-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-08 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment Hayretdin Bahsi, Neha Nagaraja Published: 2026-03-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-08 | cs.CR | ai-safety, cscr, preprint | E7 / R4 (94%) | - |
| A Blockchain-based Traceability System for AI-Driven Engine Blade Inspection Eman Ouda, Khaled Salah, Mahmoud Hafez, Mohammed A. Mohammed Eltoum Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-09 | cs.CR | ai-safety, cscr, preprint | E8 / R4 (96%) | - |
| NetDiffuser: Deceiving DNN-Based Network Attack Detection Systems with Diffusion-Generated Adversarial Traffic Abu Saleh Md Tayeen, Huiping Cao, Jayashree Harikumar, Jiefei Liu Published: 2026-03-09Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-09 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security Andrew Chin, Brian Junekyu Lee, Cen Zhang, Dongkwan Kim Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-09 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation Carsten Maple, Kayvan Atefi, Omar Santos, Petar Radanliev Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-03-09 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E6 / R3 (96%) | - |
| Security Considerations for Multi-agent Systems Dheeraj Arremsetty, Moses Ndebugre, Tam Nguyen Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-09 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| SplitAgent: A Privacy-Preserving Distributed Architecture for Enterprise-Cloud Agent Collaboration Jianshu She Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-09 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (95%) | - |
| Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents Abhinaba Basu Published: 2026-03-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-09 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |