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 |
|---|---|---|---|---|---|
| ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models Harry Owiredu-Ashley Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (98%) | - |
| AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations Md Rayhanur Rahman, Raj Patel, Shahram Rahimi, Shaswata Mitra Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models Ali Raza, Gurang Gupta, Jibesh Patra, Nikolay Matyunin Published: 2026-03-10Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-10 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities Kangjie Lu, Nanzi Yang, Weiheng Bai Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors Ailiya Borjigin, Ben Bilski, Igor Stadnyk, Serhii Hovorov Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| MCP-in-SoS: Risk assessment framework for open-source MCP servers Abu Saleh Md Tayeen, Miguel Antonio Guirao Aguilera, Pratyay Kumar, Satyajayant Misra Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (95%) | - |
| Multilingual AI-Driven Password Strength Estimation with Similarity-Based Detection Nikitha M. Palaniappan, Ying He Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (93%) | - |
| Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference Fan Yang Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, alignment-training, cscr, preprint | E6 / R4 (97%) | - |
| TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning Shujie Yang, Sizhe Huang Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (96%) | - |
| Why LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch Generation Amir Al-Maamari Published: 2026-03-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-10 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection David Aspinall, Eirik H酶yheim, Gudmund Grov, Magnus Wiik Eckhoff Published: 2026-03-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-11 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks Anderson R. Avila, Kelton A. P. Costa, Nasim Soltani, Raphael Khoury Published: 2026-03-11Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-11 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E6 / R4 (97%) | - |
| Na茂ve Exposure of Generative AI Capabilities Undermines Deepfake Detection Chanwoo Hwang, Jae Hong Seo, Minsu Kim, Sunpill Kim Published: 2026-03-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-11 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (93%) | - |
| Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning Xian Qin, Xiaohu Tang, Xue Yang Published: 2026-03-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-11 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey Bo Li, Dawn Song, Juhee Kim, Shi Qiu Published: 2026-03-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-11 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (99%) | - |
| WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference Gaoyi Wu, Hao Wang, Lingfeng Yao, Miao Pan Published: 2026-03-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-11 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (95%) | - |
| Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems Anjo Vahldiek-Oberwagner, Jose Sanchez Vicarte, Mohit Tiwari, Prateek Sahu Published: 2026-03-12Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-12 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models Dusit Niyato, Haomiao Yang, Kunlan Xiang, Meng Hao Published: 2026-03-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-12 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (97%) | - |
| Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats Changhua Meng, Jialuo Chen, Jianan Ma, Jiaqi Bai Published: 2026-03-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-12 | cs.CR | ai-safety, cscr, preprint | E8 / R3 (95%) | - |
| The Mirror Design Pattern: Strict Data Geometry over Model Scale for Prompt Injection Detection J Alex Corll Published: 2026-03-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-12 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks Junjie Chu, Michael Backes, Savvas Zannettou, Yang Zhang Published: 2026-03-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-12 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (93%) | - |
| You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents Ching-Yu Kao, Eric Hanchen Jiang, Pengcheng Zhou, Philip Sperl Published: 2026-03-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-12 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (97%) | - |
| Towards Agentic Honeynet Configuration Danilo Giordano, Federico Mirra, Idilio Drago, Marco Mellia Published: 2026-03-14Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-14 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (95%) | - |
| AEX: Non-Intrusive Multi-Hop Attestation and Provenance for LLM APIs Yongjie Guan Published: 2026-03-15Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-15 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Cryptographic Runtime Governance for Autonomous AI Systems: The Aegis Architecture for Verifiable Policy Enforcement Adam Massimo Mazzocchetti Published: 2026-03-15Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-15 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (96%) | - |
| Membership Inference for Contrastive Pre-training Models with Text-only PII Queries Hongyi Zhang, Ruoxi Cheng, Yiyan Huang, Yizhong Ding Published: 2026-03-15Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-15 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| State-Dependent Safety Failures in Multi-Turn Language Model Interaction Han Qiu, Jie Zhang, Nenghai Yu, Pengcheng Li Published: 2026-03-15Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-15 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| $p^2$RAG: Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval Cong Wang, Jijia Yang, Mingyue Wang, Xiaohua Jia Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats Bingxue Zhang, Feida Zhu, Yang Gao, Yang Shi Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (94%) | - |
| BadLLM-TG: A Backdoor Defender powered by LLM Trigger Generator Haifang Zhou, Heng Gao, Ruyi Zhang, Songlei Jian Published: 2026-03-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-16 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |