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 |
|---|---|---|---|---|---|
| ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers Chaozhuo Li, Chenxu Wang, Jinyu Hou, Litian Zhang Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E5 / R4 (97%) | - |
| Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search Geng Hong, Min Yang, Xudong Pan, Yulin Shen Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage Bell Eapen, Manjusha Sumasadan, Md Rasel Al Mamun, Nikhil Kumar Dora Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage Bell Eapen, Elyson De La Cruz, Manjusha Sumasadan, Md Rasel Al Mamun Published: 2026-03-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-25 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (96%) | - |
| Agent Audit: A Security Analysis System for LLM Agent Applications Haiyue Zhang, Yi Nian, Yue Zhao Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (98%) | - |
| AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents Haotian Zhu, Minhui Xue, Shuchao Pang, Tian Dong Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Agent-Sentry: Bounding LLM Agents via Execution Provenance Konstantinos Psounis, Rohan Sequeira, Stavros Damianakis, Umar Iqbal Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution Chaowei Xiao, Gelei Deng, Jiawen Zhang, Jie Zhang Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (99%) | - |
| Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs Chuanchao Zang, Jianing Wang, Li Wang, Peng Zhan Published: 2026-03-24Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-24 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Privacy-Aware Smart Cameras: View Coverage via Socially Responsible Coordination Chuhao Qin, Evangelos Pournaras, Lukas Esterle Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (93%) | - |
| Robust Safety Monitoring of Language Models via Activation Watermarking Daniil Ognev, Nils Lukas, Samuele Poppi, Toluwani Aremu Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Targeted Adversarial Traffic Generation : Black-box Approach to Evade Intrusion Detection Systems in IoT Networks Ishak Charfi, Islam Debicha, Jean-Michel Dricot, Mehdi Sehaki Published: 2026-03-24Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-24 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E4 / R3 (97%) | - |
| The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense Anuj Kaul, Qianlong Lan Published: 2026-03-24Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-24 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (98%) | - |
| CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training Chenkai Wang, Gang Wang, Haoyu Zhai, Huan Zhang Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (93%) | - |
| Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models Stephan Kleber, Tom Biskupski Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| Q-AGNN: Quantum-Enhanced Attentive Graph Neural Network for Intrusion Detection Devashish Chaudhary, Shiva Raj Pokhrel, Sutharshan Rajasegarar Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| SecureBreak -- A dataset towards safe and secure models Antonino Nocera, Marco Arazzi, Vignesh Kumar Kembu Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (95%) | - |
| STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving Dawson Stoller, James Hugglestone, Ryan Schmidt, Samuel Jacob Chacko Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (96%) | - |
| Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models Roy Ka-Wei Lee, Rui Yang Tan, Yujia Hu Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, alignment-training, cscr, preprint | E5 / R3 (97%) | - |
| Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks Feiyang Li, Hao Hu, Hongwei Zhou, Jiang Wu Published: 2026-03-23Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-23 | cs.CR | ai-safety, cscr, preprint | E7 / R4 (98%) | - |
| DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns Thomas Bauschert, Trung V. Phan Published: 2026-03-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-22 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| DeepXplain: XAI-Guided Autonomous Defense Against Multi-Stage APT Campaigns Thomas Bauschert, Trung V. Phan Published: 2026-03-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-22 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Fingerprinting Deep Neural Networks for Ownership Protection: An Analytical Approach Changqing Luo, Guang Yang, Yihang Chen, Ziye Geng Published: 2026-03-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-22 | cs.CR | ai-safety, cscr, preprint | E4 / R2 (94%) | - |
| Is Monitoring Enough? Strategic Agent Selection For Stealthy Attack in Multi-Agent Discussions Haoxuan Qu, Hossein Rahmani, Jun Liu, Qiuchi Xiang Published: 2026-03-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-22 | cs.CR | ai-safety, cscr, preprint | E6 / R3 (94%) | - |
| When Convenience Becomes Risk: A Semantic View of Under-Specification in Host-Acting Agents Di Lu, Jianfeng Ma, Ke Cheng, Lele Zheng Published: 2026-03-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-22 | cs.CR | ai-safety, cscr, preprint | E4 / R3 (92%) | - |
| AC4A: Access Control for Agents Dan Grossman, Reshabh K Sharma Published: 2026-03-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-21 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (96%) | - |
| Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents Uchi Uchibeke Published: 2026-03-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-21 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (98%) | - |
| Cyber Deception for Mission Surveillance via Hypergame-Theoretic Deep Reinforcement Learning Ahmed H. Anwar, Charles Kamhoua, Jin-Hee Cho, Munindar P. Singh Published: 2026-03-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-21 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (97%) | - |
| T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search Hyomin Lee, Sangwoo Park, Seanie Lee, Sohyun An Published: 2026-03-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-03-21 | cs.CR | ai-safety, cscr, preprint | E5 / R3 (94%) | - |
| Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models Feng Chang, Jian Zhu, Ke Tang, Li Wang Published: 2026-03-20Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-03-20 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E4 / R3 (96%) | - |