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 |
|---|---|---|---|---|---|
| Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study Dev Prashant Mistry, Diego Fernandez Arias, Ren Wang, Yibo Hu Published: 2026-07-27Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-07-27 | cs.CR | ai-safety, cscr, preprint | E12 / R11 (91%) | 15 |
| Latent Stability Analysis of Malware Representations Under Feature-Space Perturbations Bamidele Ajayi, Ken McGarry Published: 2026-07-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-27 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (92%) | - |
| ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour Jianhang Xie, Sicheng Tan, Vishnu Naresh Boddeti, Zhichao Lu Published: 2026-07-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-26 | cs.CR | ai-safety, cscr, preprint | - | - |
| DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory Xingyang Yu Published: 2026-07-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-26 | cs.CR | ai-safety, cscr, preprint | - | - |
| Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric Alexios Lekidis, Nikolaos Kekatos, Panagiotis Katsaros, Stylianos Basagiannis Published: 2026-07-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-26 | cs.CR | ai-safety, cscr, preprint | - | - |
| The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting Gurjot Singh, Ishpuneet Singh, Maninder Singh, Shreyas Mahajan Published: 2026-07-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-26 | cs.CR | ai-safety, cscr, preprint | - | - |
| TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Disha Singhania, Jeenal Chaudhary, Kosuru Yuvaraj, Rohit Patel Published: 2026-07-26Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-26 | cs.CR | ai-safety, cscr, preprint | - | - |
| False Prophets: On the Security of World Models in Agentic Systems Anna Wimbauer, Erik Imgrund, Klim Kireev, Konrad Rieck Published: 2026-07-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-25 | cs.CR | ai-safety, cscr, preprint | - | - |
| Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios Bei Wang, Feng Wei, Lixun Ma, Lorenzo Cavallaro Published: 2026-07-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-25 | cs.CR | ai-safety, cscr, preprint | - | - |
| Traceable LLM Reasoning for Fake-Order Fraud Detection Bingsong Xu, Jiarong Xu, Siqi You, Xinjian Peng Published: 2026-07-25Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-25 | cs.CR | ai-safety, cscr, preprint | - | - |
| Agent Security Needs Redefinition through a Holistic Framework Chenguang Wang, Dawn Song, Jingxuan He, Kyle Montgomery Published: 2026-07-24Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-07-24 | cs.CR | ai-safety, cscr, preprint | E13 / R7 (93%) | 15 |
| Practical Graph Optimisation and AI-Driven Models for Active Directory Security Hardening Huy Q. Ngo Published: 2026-07-24Area: cs.CRCitations: 107 Tags: ai-safety, cscr, preprint | 2026-07-24 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (89%) | 107 |
| Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks Ads Dawson, Brian Greunke, Michael Kouremetis, Raja Sekhar Rao Dheekonda Published: 2026-07-23Area: cs.CRCitations: 24 Tags: ai-safety, cscr, preprint | 2026-07-23 | cs.CR | ai-safety, cscr, preprint | E10 / R6 (91%) | 24 |
| ToolGuardian: Declarative Security for AI Agent-Tool Interactions Arun Ravindran, Saurabh Deochake Published: 2026-07-23Area: cs.CRCitations: 20 Tags: ai-safety, cscr, preprint | 2026-07-23 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | 20 |
| Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation D. Fern谩ndez-Fern谩ndez, M. Llamb铆-Morillas Published: 2026-07-23Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-07-23 | cs.CR | ai-safety, cscr, preprint | E14 / R13 (93%) | 22 |
| An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports Jiahao Gu, Ning Hu, Wenbo Hou, Wenjian Luo Published: 2026-07-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (89%) | - |
| Defense Against LLM Backdoors using Critical Neuron Isolation Pruning Haoyu Wang, Kailong Wang, Ling Shi, Xingshuo Han Published: 2026-07-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E15 / R11 (90%) | - |
| Evaluating Large Language Models for Symbolic Security Protocol Analysis Derek Enodolomwanyi, Ioannis Sfyrakis, Paolo Modesti, Syed Ahmed Published: 2026-07-22Area: cs.CRCitations: 27 Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (91%) | 27 |
| FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense Chenyu Zhou, Kunlin Li, Shuaishuai Zhang, Wei Huang Published: 2026-07-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (89%) | - |
| Geometric Configurations of Perturbed Jailbreak Prompts Andres Algaba, Lynn Delcon, Vincent Ginis Published: 2026-07-22Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-07-22 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E9 / R7 (94%) | - |
| GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning Jiamou Liu, Liehuang Zhu, Pengtao Kou, Xiaomei Yuan Published: 2026-07-22Area: cs.CRCitations: 21 Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E9 / R6 (88%) | 21 |
| HijackKV: New Threat in Position-Independent KV Cache Reuse Huan Zhang, Yichi Zhang, Yuchen Yang, Zhiqi Wang Published: 2026-07-22Area: cs.CRCitations: 65 Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E9 / R5 (91%) | 65 |
| IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests Ankur Singh, Jinqiu Yang, Tse-Hsun Chen Published: 2026-07-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E14 / R14 (91%) | - |
| Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis Adel ElZemity, Budi Arief, Shujun Li Published: 2026-07-22Area: cs.CRCitations: 75 Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (91%) | 75 |
| Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection Shrinidhi Sridhar, Vikas K. Malviya Published: 2026-07-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (92%) | - |
| The Ethics of Autonomous AI Agents for Offensive Security Andreas Happe, Jasmin Wachter, J眉rgen Cito Published: 2026-07-22Area: cs.CRCitations: 59 Tags: ai-safety, cscr, preprint | 2026-07-22 | cs.CR | ai-safety, cscr, preprint | E14 / R13 (88%) | 59 |
| Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents Amin Kharraz, Behzad Ousat, Dillan Bailey, Lalchandra Rampersaud Published: 2026-07-21Area: cs.CRCitations: 47 Tags: ai-safety, cscr, preprint | 2026-07-21 | cs.CR | ai-safety, cscr, preprint | E10 / R6 (92%) | 47 |
| Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer Rajat Srivastava Published: 2026-07-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-21 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (89%) | - |
| CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization Behnoosh Zamanlooy, David B. Emerson, Deval Pandya, Masoumeh Shafieinejad Published: 2026-07-21Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-07-21 | cs.CR | ai-safety, cscr, preprint | E11 / R6 (89%) | 15 |
| Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents Jineok Kim, Minseung Kang, Myungsub Choi, SangJin Park Published: 2026-07-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-21 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (91%) | - |