Instant research discovery
Search and browse ingested papers with intelligence signals and fast filtering.
| Paper | Year | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| A Blockchain-based Traceability System for AI-Driven Engine Blade Inspection Yusra Abdulrahman, Khaled Salah, Mohammed A. Mohammed Eltoum, Eman Ouda Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E8 / R4 (96%) | - |
| ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models Harry Owiredu-Ashley Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (98%) | - |
| Adversarial attacks against Modern Vision-Language Models Alejandro Paredes La Torre Year: 2026Area: cs.CRCitations: - Tags: ai-safety, adversarial-robustness, cscr, preprint | 2026 | cs.CR | ai-safety, adversarial-robustness, cscr, preprint | - | - |
| Agent Control Protocol: Admission Control for Agent Actions Marcelo Fernandez Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations Raj Patel, Shahram Rahimi, Shaswata Mitra, Sudip Mittal Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models Nikolay Matyunin, Gurang Gupta, Jibesh Patra, Ali Raza Year: 2026Area: cs.CRCitations: - Tags: ai-safety, adversarial-robustness, cscr, preprint | 2026 | cs.CR | ai-safety, adversarial-robustness, cscr, preprint | E5 / R3 (96%) | - |
| Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats Bingxue Zhang, Yanyan Shen, Yang Gao, Yang Shi Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs Wei Zhao, Hanxun Huang, Yunhan Zhao, Zhe Li Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (99%) | - |
| Beyond TVLA: Anderson-Darling Leakage Assessment for Neural Network Side-Channel Leakage Detection Xiaolu Hou, Jakub Breier, Ján Mikulec Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare Saikat Maiti Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems Jose Sanchez Vicarte, Anjo Vahldiek-Oberwagner, Sarbartha Banerjee, Prateek Sahu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, adversarial-robustness, cscr, preprint | 2026 | cs.CR | ai-safety, adversarial-robustness, cscr, preprint | - | - |
| ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation Haochen Zhao, Shaoyang Cui Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, safety-evaluation, preprint | 2026 | cs.CR | ai-safety, cscr, safety-evaluation, preprint | - | - |
| ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems Jiangrong Wu, Huanran Chen, Jun Sun, Haolin Wu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities Weiheng Bai, Nanzi Yang, Kangjie Lu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT Campaigns Trung V. Phan, Thomas Bauschert, Tri Gia Nguyen Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models Ruichen Zhang, Dusit Niyato, Yijing Liu, Haomiao Yang Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning Sunpreet S. Arora, Shan Jin, Shenao Yan, Yizhen Wang Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models Raja Muthalagu, Pranav M Pawar, Mithun Mukherjee, Isha Andrade Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Detecting and Eliminating Neural Network Backdoors Through Active Paths with Application to Intrusion Detection David Aspinall, Robert Flood, Magnus Wiik Eckhoff, Gudmund Grov Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs Quanyan Zhu, Ya-Ting Yang Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation Bo Jiang Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
| ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code Elzo Brito dos Santos Filho Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (96%) | - |
| Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks Raphael Khoury, Kelton A. P. Costa, Nasim Soltani, Shayan Nejadshamsi Year: 2026Area: cs.CRCitations: - Tags: ai-safety, adversarial-robustness, cscr, preprint | 2026 | cs.CR | ai-safety, adversarial-robustness, cscr, preprint | - | - |
| Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents Simone Aonzo, Daniele Perito, Merve Sahin, Aurélien Francillon Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors Ben Bilski, Sofiia Pidturkina, Igor Stadnyk, Ailiya Borjigin Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning Panos Papadimitratos, Sheng Liu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents Tianyu Du, Xiaolei Zhang, Hao Peng, Zhe Liu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (97%) | - |
| Functional Subspace Watermarking for Large Language Models Junchi Yao, Lijie Hu, Zikang Ding, Suling Wu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | - | - |
| Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems Kaidi Xu, Xuelong Dai, Yue Zhang, Minghui Xu Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice Yuxu Ge Year: 2026Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (97%) | - |
Showing 30 of 70 papers on page 1.