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 |
|---|---|---|---|---|---|
| VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj, Maanak Gupta Published: 2026-07-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-10 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (87%) | - |
| Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions Anjun Gao, Minghong Fang, Yueyang Quan, Zhuqing Liu Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E24 / R8 (88%) | - |
| From Legacy Documentation to OSCAL: An MCP-Based Agent Pipeline for Threat-Informed Continuous Compliance in Critical Infrastructure Lea Roxanne Muth, Marian Margraf Published: 2026-07-09Area: cs.CRCitations: 26 Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (94%) | 26 |
| Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models Alfonso S谩nchez-Maci谩n, Hugo Garc铆a Cuesta, Pablo Mateo Torrej贸n Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E9 / R9 (94%) | - |
| Out of Sight: Compression-Aware Content Protection against Agentic Crawlers Xuefei Wang Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (89%) | - |
| Prismata: Confining Cross-Site Prompt Injection in Web Agents Alp Eren Ozdarendeli, Corban Villa, Raluca Ada Popa, Sijun Tan Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (91%) | - |
| Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts Lea Roxanne Muth, Marian Margraf Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E12 / R7 (90%) | - |
| TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories Jiaojiao Jiang, Liming Zhu, Xiaoyan Feng, Xiaoyu Li Published: 2026-07-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E15 / R15 (96%) | - |
| Trivial Prompt Reframing Bypasses Safety Guardrails in Google艣 MedGemma-4B Avi-ad Avraam Buskila Published: 2026-07-09Area: cs.CRCitations: 19 Tags: ai-safety, cscr, preprint | 2026-07-09 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (93%) | 19 |
| Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents Harry Owiredu-Ashley Published: 2026-07-08Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-07-08 | cs.CR | ai-safety, cscr, preprint | E13 / R10 (89%) | 15 |
| Closed-Loop Dynamic Validator Node Scaling in Private Substrate Blockchains Using Takagi-Sugeno Fuzzy Inference Ayinde M. Usman, Clement N. Nyirenda, Thandile Nododile Published: 2026-07-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-08 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (92%) | - |
| Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies Kiarash Ahi, Saeed Valizadeh Published: 2026-07-08Area: cs.CRCitations: 70 Tags: ai-safety, cscr, preprint | 2026-07-08 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (92%) | 70 |
| Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs Anupam Wagle, Chaowei Zhang, Ifrat Ikhtear Uddin, Longwei Wang Published: 2026-07-08Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, interpretability, preprint | 2026-07-08 | cs.CR | adversarial-robustness, ai-safety, cscr, interpretability, preprint | E6 / R6 (91%) | - |
| Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems Anjun Gao, Minghong Fang, Yueyang Quan, Yufei Xia Published: 2026-07-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-08 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (89%) | - |
| i-EXAM: Instructable and Explainable Attack Connectivity Graph Modeler Indrajit Ray, Indrakshi Ray, Rakesh Podder, Sarath Sreedharan Published: 2026-07-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (88%) | - |
| PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning Anil Kumar Pradhan, Carsten Maple, Graham Cormode, Harsh Kasyap Published: 2026-07-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E17 / R16 (92%) | - |
| Security and Privacy in Agentic AI: Grand Challenges and Future Directions Adam Jenkins, Agnieszka Kitkowska, Caterina Maidhof, Diego Paracuellos Published: 2026-07-07Area: cs.CRCitations: 90 Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | 90 |
| The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities Mohammadreza Rashidi Published: 2026-07-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (93%) | - |
| Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations Mohammadreza Rashidi Published: 2026-07-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (91%) | - |
| When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems Chao Wang, Haowen Xu, Jun Dai, Lei Ma Published: 2026-07-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-07 | cs.CR | ai-safety, cscr, preprint | E6 / R6 (94%) | - |
| Agent Data Injection Attacks are Realistic Threats to AI Agents Byoungyoung Lee, Jihyeon Jeong, Juhee Kim, Luyi Xing Published: 2026-07-06Area: cs.CRCitations: 30 Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (94%) | 30 |
| aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents Sai Varun Kodathala Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (93%) | - |
| Evaluating calibrated refusal and safe usefulness in dual-use biology settings Adam J. Meyer, Arjun Banerjee, Christina M. Agapakis, Daniel Fulop Published: 2026-07-06Area: cs.CRCitations: 18 Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E9 / R9 (94%) | 18 |
| Full-range Binary Classifier Calibration for Stable Model Updates in Production Konstantin Berlin Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (95%) | - |
| Privacy-Preserving Robustness Verification for Neural Networks Meng Sun, Nianyun Song, Rongfang Bie, Xiaokun Luan Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | - |
| Privilege and confidentiality in generative AI workflows Thomas Melham, V谩clav Jane膷ek Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (94%) | - |
| RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities Alvyn Kang, Ang茅lica Moreira, Angel X. Chang, Arnell Kang Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E17 / R16 (93%) | - |
| Selective Disclosure Watermarking for Large Language Models Qi Long, Xiang Li, Xuyang Chen, Yangxinyu Xie Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (95%) | - |
| TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction Gregory Blanc, Mouhamed Amine Bouchiha Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (91%) | - |
| TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction Gregory Blanc, Mouhamed Amine Bouchiha Published: 2026-07-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-06 | cs.CR | ai-safety, cscr, preprint | E11 / R13 (91%) | - |