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 |
|---|---|---|---|---|---|
| Privacy-Preserving LLMs Routing Qian Lou, Reza Shirkavand, Shangqian Gao, Xidong Wu Published: 2026-04-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-17 | cs.CR | ai-safety, cscr, preprint | E13 / R10 (96%) | - |
| CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution Ray C. C. Cheung, Ruiyi Guo, Shutong Jin Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (97%) | - |
| CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems Edip G眉m眉艧, 陌pek Abas谋kele艧 Turgut Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (100%) | - |
| enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways Alfredo Metere Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E7 / R4 (96%) | - |
| Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives Daeyeon Son Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E6 / R4 (97%) | - |
| SafeDream: Safety World Model for Proactive Early Jailbreak Detection Bo Yan, Song Wang, Weikai Lin, Yada Zhu Published: 2026-04-18Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-04-18 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E10 / R5 (99%) | - |
| Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks Hakan T. Otal, Joseph M. Escobar, Michael H. Conaway, Tyler H. Merves Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E9 / R4 (98%) | - |
| Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning Jiachen Qian Published: 2026-04-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-18 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (98%) | - |
| Decentralised Trust and Security Mechanisms for IoT Networks at the Edge: A Comprehensive Review Khandoker Ashik Uz Zaman, Mahdi H. Miraz, Mohammed N. M. Ali Published: 2026-04-19Area: cs.CRCitations: 30 Tags: ai-safety, cscr, preprint | 2026-04-19 | cs.CR | ai-safety, cscr, preprint | E12 / R6 (97%) | 30 |
| Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories Aditi Raghunathan, Ivan Bercovich, Ivgeni Segal, Kexun Zhang Published: 2026-04-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-19 | cs.CR | ai-safety, cscr, preprint | E9 / R6 (99%) | - |
| Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation Fuji Ren, Jiawen Deng, Mingfei Zhang, Wentao Zhang Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E8 / R4 (98%) | - |
| Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs Ziyang Liu Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E9 / R5 (95%) | - |
| Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks Md Rysul Kabir, Zoran Tiganj Published: 2026-04-20Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-04-20 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E9 / R4 (95%) | - |
| Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks Jin Zhao, Marta Kne啪evi膰, Tanja K盲ser Published: 2026-04-20Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-04-20 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E9 / R4 (98%) | - |
| ExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks Lauri Loven, Panos Kostakos, Saeid Sheikhi Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E10 / R6 (98%) | - |
| From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers Changran Xu, Fangxin Liu, Haomin Li, Jianrong Ding Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E13 / R6 (98%) | - |
| Owner-Harm: A Missing Threat Model for AI Agent Safety Dongcheng Zhang, Yiqing Jiang Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E8 / R4 (97%) | - |
| Position: No Retroactive Cure for Infringement during Training Ichiro Sakata, Junichiro Mori, Masaru Isonuma, Satoru Utsunomiya Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E9 / R4 (95%) | - |
| RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs Achyuta Muthuvelan, Asini Subanya, Boubacar Ballo, Boyuan Chen Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E10 / R6 (98%) | - |
| Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents Wenpeng Xu Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E9 / R5 (98%) | - |
| Tight Auditing of Differential Privacy in MST and AIM Bogdan Kulynych, Georgi Ganev, Meenatchi Sundaram Muthu Selva Annamalai Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E8 / R4 (97%) | - |
| Towards Optimal Agentic Architectures for Offensive Security Tasks Arthur Gervais, Isaac David Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E13 / R4 (100%) | - |
| Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective Huang Nianchen, Meifang Chen, Michael R. Lyu, Yichen Li Published: 2026-04-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-20 | cs.CR | ai-safety, cscr, preprint | E8 / R3 (94%) | - |
| An AI Agent Execution Environment to Safeguard User Data Avi Verma, Konstantinos Kallas, Lillian Tsai, Robert Stanley Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-21 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (99%) | - |
| Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps Alankrit Chona, Ambuj Kumar, Igor Kozlov Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-04-21 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E11 / R6 (97%) | - |
| Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps Alankrit Chona, Ambuj Kumar, Igor Kozlov Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-04-21 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E9 / R4 (98%) | - |
| DP-FlogTinyLLM: Differentially private federated log anomaly detection using Tiny LLMs Isaiah Thompson, Ritwik Bhattacharya, Tanmay Sen Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-21 | cs.CR | ai-safety, cscr, preprint | E11 / R7 (98%) | - |
| ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety Cheng Qian, Jiaming Zhang, Kun Wang, Liang Lin Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-04-21 | cs.CR | ai-safety, cscr, preprint | E10 / R5 (97%) | - |
| Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery Abhinav Agarwal Published: 2026-04-21Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-04-21 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E8 / R4 (98%) | - |
| Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio Published: 2026-04-21Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-04-21 | cs.CR | ai-safety, alignment-training, cscr, preprint | E7 / R4 (96%) | - |