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 |
|---|---|---|---|---|---|
| Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems Rudrendu Kumar Paul, Sourav Nandy Published: 2026-09-19Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E13 / R10 (93%) | 15 |
| Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach Bata Vasic, Iva Vasic, Jes煤s Mu帽oz-C谩diz Published: 2026-09-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (96%) | - |
| From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation Joas Antonio dos Santos Barbosa Published: 2026-09-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (91%) | - |
| LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication Liang Zhao, Yuzhu Mao Published: 2026-09-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (89%) | - |
| MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning Changyue Jiang, Geng Hong, Jiarun Dai, Jiayi Wang Published: 2026-09-19Area: cs.CRCitations: 46 Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (91%) | 46 |
| SelfOp: An Optimization Algorithm for Self-Improving Security Agents Christopher Kruegel, Gianluca Stringhini, Giovanni Vigna, Saad Ullah Published: 2026-09-19Area: cs.CRCitations: 42 Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (88%) | 42 |
| The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents Pritom Bhowmik Published: 2026-09-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E8 / R10 (95%) | - |
| When Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust Evidence Huafu Li, Jia Xia Published: 2026-09-19Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-19 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | - |
| CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices An Wang, Jing Liang, Jingqi Zhang, Liehuang Zhu Published: 2026-09-18Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-09-18 | cs.CR | ai-safety, cscr, preprint | E12 / R10 (91%) | 45 |
| CIPL: A Channel-Aware Framework for Recoverable Privacy Leakage in LLM Agents Chen Hou, Feng Xia, Guolong Zheng, Guosen Wu Published: 2026-09-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-18 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (90%) | - |
| HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference Byeongseo Min, Yongjune Kim, Yongwoo Lee, Young-Sik Kim Published: 2026-09-18Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-18 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E10 / R10 (94%) | - |
| Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems Eva Maia, Isabel Pra莽a, Pedro Pereira Published: 2026-09-18Area: cs.CRCitations: 21 Tags: ai-safety, cscr, preprint | 2026-09-18 | cs.CR | ai-safety, cscr, preprint | E10 / R11 (93%) | 21 |
| TERMon: Detecting Persistent Behavioral Threats in Edge AI via Hardware-Native Ternary Runtime Monitor Arish Sateesan, Edlira Dushku Published: 2026-09-18Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-18 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | 15 |
| Zero-Trust Authorization and Discovery for Enterprise MCP Huan Li, Srinivasan Manoharan, Yuwei Wang Published: 2026-09-18Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint | 2026-09-18 | cs.CR | ai-safety, cscr, preprint | E12 / R7 (94%) | 12 |
| A Scalable Trust Discovery Architecture for the Internet of Agents Hongtao Li, Jiankang Yao, Song Zhang, Xiaojun Zhang Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E8 / R9 (92%) | - |
| ClashBench: Conflicts Leading Agents to Seize and Harm Dadi Guo, Dongrui Liu, Qingyu Liu, Xia Hu Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (94%) | - |
| Fingerprinting Multimodal Large Language Models Chao Huang, Kejiang Chen, Meng Tong Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E11 / R7 (90%) | - |
| Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape Andrew Cheng, James Mickens, Sarah Radway, Vijay Janapa Reddi Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (90%) | - |
| Loopjacking: Hijacking Human-in-the-Loop Approval Adithyan Arun Kumar Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E8 / R5 (95%) | - |
| Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents Alex Remedios, Fabien Roger, John Hughes, Simon Storf Published: 2026-09-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E12 / R11 (94%) | - |
| SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes Mengxiao Wang, Nitesh Saxena Published: 2026-09-17Area: cs.CRCitations: 54 Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E16 / R12 (92%) | 54 |
| Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies Chuhong Xu, Gangzhen Qian, Hang Xiao, Kainan Zhou Published: 2026-09-17Area: cs.CRCitations: 9 Tags: ai-safety, cscr, preprint | 2026-09-17 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (89%) | 9 |
| ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions Chen Hou, Guosen Wu, Guoxiong Long, Huizhen Huang Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E14 / R14 (93%) | - |
| ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions Chen Hou, Guosen Wu, Guoxiong Long, Huizhen Huang Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E14 / R11 (92%) | - |
| AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment Asif Ekbal, Kshitij Mishra, Sai Sri Pushpa Jampani Published: 2026-09-16Area: cs.CRCitations: 15 Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, alignment-training, cscr, preprint | E12 / R8 (93%) | 15 |
| Autonomy in Check: Governor-Mediated Adaptive Security at the Edge Erkki Harjula, Flavio Esposito, Ijaz Ahmad Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | - |
| Echo: Learning-based Matching Decompilation using Trusted Back Translation Aarsh Chaube, Jos茅 Wesley De Souza Magalh茫es, Jun Bi, Michael O'Boyle Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (90%) | - |
| MiST: Mid-Training LLMs for Cybersecurity Elad Ben Zaken, Elad Guttman, Oded Ovadia, Orly Moreno Kadosh Published: 2026-09-16Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (87%) | 15 |
| PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows Chen Hou, Guolong Zheng, Guosen Wu, Tao Huang Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E9 / R5 (90%) | - |
| PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs Dipo Dunsin, Mohamed Chahine Ghanem, Mohammed Almaiah, Rushabh Vipulkumar Patel Published: 2026-09-16Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-16 | cs.CR | ai-safety, cscr, preprint | E12 / R11 (91%) | - |