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 |
|---|---|---|---|---|---|
| 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%) | - |
| 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%) | - |
| 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 |
| AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement Jian Sheng Wang Published: 2026-02-27Area: cs.CRCitations: 31 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (90%) | 31 |
| Challenges in Enabling Private Data Valuation Tianhao Wang, Varun Chandrasekaran, Yiwei Fu Published: 2026-02-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (90%) | - |
| Empowering Future Cybersecurity Leaders: Advancing Students through FINDS Education for Digital Forensic Excellence Jerry F. Miller, Naveen Kumar Chaudhary, Pronab Mohanty, Subhash Gurappa Published: 2026-02-27Area: cs.CRCitations: 40 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (92%) | 40 |
| Enhancing Continual Learning for Software Vulnerability Prediction: Addressing Catastrophic Forgetting via Hybrid-Confidence-Aware Selective Replay for Temporal LLM Fine-Tuning Alejandro Guerra-Manzanares, Hayretdin Bahsi, Xuhui Dou Published: 2026-02-27Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | 45 |
| Exploring Robust Intrusion Detection: A Benchmark Study of Feature Transferability in IoT Botnet Attack Detection Alejandro Guerra-Manzanares, Jialin Huang Published: 2026-02-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E14 / R14 (94%) | - |
| Formal Analysis and Supply Chain Security for Agentic AI Skills Varun Pratap Bhardwaj Published: 2026-02-27Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (92%) | 45 |
| Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking Chenxu Fu, Jingjie Zheng, Wei Xu, Zhicheng Fang Published: 2026-02-27Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-02-27 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E10 / R8 (91%) | - |
| LiaisonAgent: An Multi-Agent Framework for Autonomous Risk Investigation and Governance Chuanming Tang, Ling Qing, Shifeng Chen Published: 2026-02-27Area: cs.CRCitations: 21 Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (91%) | 21 |
| MI$^2$DAS: A Multi-Layer Intrusion Detection Framework with Incremental Learning for Securing Industrial IoT Networks Alejandro Guerra-Manzanares, Wei Lian Published: 2026-02-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-27 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (93%) | - |
| 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 |
| AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification Bowen Xiao, Hongxin Hu, Jiawei Liu, Jinlin Fan Published: 2026-02-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (91%) | - |
| Automated Vulnerability Detection in Source Code Using Deep Representation Learning C. Seas, G. Fitzpatrick, J. A. Hamilton, M. C. Carlisle Published: 2026-02-26Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | 12 |
| Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation Kennedy Edemacu, Mohammad Mahdi Shokri Published: 2026-02-26Area: cs.CRCitations: 61 Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (92%) | 61 |
| IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation Binhang Yuan, Dawn Song, Jiaheng Zhang, Linyu Wu Published: 2026-02-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (92%) | - |
| Learning to Generate Secure Code via Token-Level Rewards Bin Wang, Chengbin Hou, Degen Huang, Guo An Published: 2026-02-26Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (92%) | 45 |
| Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection Marcus Graves Published: 2026-02-26Area: cs.CRCitations: 7 Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E12 / R6 (95%) | 7 |
| RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration Srikumar Nayak Published: 2026-02-26Area: cs.CRCitations: 14 Tags: ai-safety, cscr, preprint | 2026-02-26 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (94%) | 14 |