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 |
|---|---|---|---|---|---|
| ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models Maanak Gupta, Maraz Mia, Mir Mehedi A. Pritom, Shovan Roy Published: 2026-08-22Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-22 | cs.CR | ai-safety, cscr, preprint | E12 / R10 (90%) | - |
| On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study Aadil Mallick, Anna Schmedding, Bill Hudson, Chris Gourley Published: 2026-08-22Area: cs.CRCitations: 52 Tags: ai-safety, cscr, preprint | 2026-08-22 | cs.CR | ai-safety, cscr, preprint | E13 / R6 (92%) | 52 |
| $Z^2$-ACT: End-to-End Verifiable Agentic Intent Control for Open 6G RAN George C. Alexandropoulos, Kapal Dev, Sunder Ali Khowaja Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (91%) | - |
| AID-Guard: Stateful Authorization for Delegated Agent Effects Leyu Dai, Songhui Guo, Yingzhe Tong Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E14 / R12 (90%) | - |
| ARQ: Agentic CodeQL Query Refinement for C/C++ Vulnerability Detection Chunyi Wang, Junfeng Yang, Penghui Li, Yunfei Ke Published: 2026-08-21Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E12 / R10 (96%) | 15 |
| ClawSentry: A Progressive Multi-Tier Security Monitor for Safeguarding Autonomous LLM Agents An Wang, BiaoJie Zeng, Chang Jin, Jingjing Qu Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E14 / R13 (92%) | - |
| SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation David Wagner, Long Lian, Sizhe Chen, Yibo Peng Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E11 / R8 (93%) | - |
| Structured but Fragile: On the Limits of LLMs in Cybersecurity Decision-Making Pasquale Malacaria, Yunxiao Zhang Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E13 / R9 (93%) | - |
| Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking Arulnidhi Karunanidhi Published: 2026-08-21Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | - | - |
| Vibe Coding and Web Application Security: A Twin-Prompt Study Darko Andro膷ec Published: 2026-08-21Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint | 2026-08-21 | cs.CR | ai-safety, cscr, preprint | E12 / R8 (93%) | 12 |
| AEGIS: Preventing Cross-Domain Resource Abuse in MCP Frederico Araujo, Shriti Priya, Teryl Taylor Published: 2026-08-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-20 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (92%) | - |
| Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents Avesta Sasan, Chongzhou Fang, Houman Homayoun, Setareh Rafatirad Published: 2026-08-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-20 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (94%) | - |
| EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models Chi Cui, Junjie Chu, Yang Zhang, Ye Leng Published: 2026-08-20Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-20 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (93%) | - |
| MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection Gelei Deng, Leo Zhang, Yi Liu, Ying Zhang Published: 2026-08-20Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-20 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (91%) | 15 |
| Autonomous Cyber Defense in Connected Vehicles: A Multi-Agent Approach to V2X Security Krishna Teja Medam Published: 2026-08-19Area: cs.CRCitations: 19 Tags: ai-safety, cscr, preprint | 2026-08-19 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (94%) | 19 |
| From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation Boubakr Nour, Chadi Assi, Makan Pourzandi, Mourad Debbabi Published: 2026-08-19Area: cs.CRCitations: 26 Tags: ai-safety, cscr, preprint | 2026-08-19 | cs.CR | ai-safety, cscr, preprint | E12 / R8 (91%) | 26 |
| COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models Anhao Xiang, Chenyu Wang, Honghui Xu, Huayue Gu Published: 2026-08-18Area: cs.CRCitations: 52 Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (91%) | 52 |
| Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets Chaochao Lu, Han Qi, Jiajia Li, Peng Yu Published: 2026-08-18Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-18 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E19 / R16 (93%) | - |
| HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety Jie Peng, Jinhao Duan, Sijia Liu, Song Wang Published: 2026-08-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E20 / R20 (97%) | - |
| Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus Kyriakos "Rock" Lambros, Steve Wilson Published: 2026-08-18Area: cs.CRCitations: 24 Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E16 / R12 (94%) | 24 |
| MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps Jing Shao, Lijun Li, Sujin Chen, Tianyi Du Published: 2026-08-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E13 / R8 (92%) | - |
| PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance Hemanth Hm, Lei Xu, Prakhar Mehrotra, Rabimba Karanjai Published: 2026-08-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (90%) | - |
| Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents Alexander Tu, Michael Tu Published: 2026-08-18Area: cs.CRCitations: 21 Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (93%) | 21 |
| The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges Boting Lu, Han Qiu, Jianshuo Dong, Jie Zhang Published: 2026-08-18Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E14 / R12 (91%) | 15 |
| When Agents Act on Web3: An Attack-Surface Survey of MCP, Skills, and Tool Calling Lei Xu, Nour Diallo, Rabimba Karanjai, Shi Published: 2026-08-18Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-18 | cs.CR | ai-safety, cscr, preprint | E12 / R7 (90%) | - |
| Authorization Before Context: A Model-Neutral Audience Boundary Against Cross-Audience Memory Leakage in Agentic Systems Sibo Liu Published: 2026-08-17Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint | 2026-08-17 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | 12 |
| CompoSkill: Compositional Skill Chain Attacks from Individually Scanner-Passing LLM Agent Skills Jialuo Chen, Jianan Ma, Jian Zhang, Mingxiao Liu Published: 2026-08-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-17 | cs.CR | ai-safety, cscr, preprint | E14 / R13 (92%) | - |
| Digital Twin Degradation: Detecting Cyber Physical Attacks via Temporal Inconsistencies Konstantinos E. Kampourakis, Sokratis Katsikas, Vasileios Gkioulos Published: 2026-08-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-17 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (94%) | - |
| Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm Hidayet Aksu Published: 2026-08-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-17 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (91%) | - |
| Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm Hidayet Aksu Published: 2026-08-17Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-17 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (90%) | - |