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 Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code Glaucia Melo, Jessica Pourleyli, Maitreyee Das Urmi Published: 2026-09-09Area: cs.CRCitations: 18 Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E12 / R14 (96%) | 18 |
| CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding Alexander V. Mantzaris, Wissam Ghantous Published: 2026-09-09Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (93%) | 15 |
| CS-Guard: Benchmarking LLM Guardrails for Code Generation Security Hung X. Nguyen, Jinyang Li, Mingyu Guo Published: 2026-09-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E24 / R22 (92%) | - |
| DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents Asif Pinjari, Mithun Paul Saint-Germain Published: 2026-09-09Area: cs.CRCitations: 42 Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (94%) | 42 |
| How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE Kai Shen, Tanyu Chen, Yi Shi Published: 2026-09-09Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, alignment-training, cscr, preprint | E10 / R11 (91%) | - |
| Learning Intrusion Response Strategies for OT Systems Duc Huy Le, Rolf Stadler Published: 2026-09-09Area: cs.CRCitations: 36 Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (95%) | 36 |
| No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers Adam Doupe, Aditya Maheshbhai Gabani, Chang Zhu, Divij Handa Published: 2026-09-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (92%) | - |
| Subgroup Membership Inference Audits of Differentially Private Synthetic Text Anil Anthony Bharath, Siew Kei Lam, Srinivasan Nandakumar, Viktor Schlegel Published: 2026-09-09Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | 22 |
| Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite Systems Eman El-Sheikh, Guillermo Francia, Hossain Shahriar, Kyle Stein Published: 2026-09-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-09 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (94%) | - |
| ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing Alex Leung, Kentaroh Toyoda, Yi Ting Shen Published: 2026-09-08Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-08 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E16 / R16 (88%) | - |
| An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks Mohammad I. Husain, Viet K. Nguyen Published: 2026-09-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-09-08 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E19 / R42 (92%) | - |
| Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks Aymene Berriche, Cathrine Shalby, Mohannad Alhanahnah, Yazan Boshmaf Published: 2026-09-08Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-08 | cs.CR | ai-safety, cscr, preprint | E21 / R10 (94%) | 15 |
| Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports Akash Prakash, Boubakr Nour, Chadi Assi, Makan Pourzandi Published: 2026-09-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-08 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (88%) | - |
| In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning Iliano Fasolino Published: 2026-09-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-08 | cs.CR | ai-safety, cscr, preprint | E9 / R6 (89%) | - |
| AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories Asif Pinjari, Mithun Paul Saint-Germain Published: 2026-09-07Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E11 / R8 (95%) | 45 |
| AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing Bin Wang, Liang Zhang, Shichang Liu, Wei Wang Published: 2026-09-07Area: cs.CRCitations: 30 Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (89%) | 30 |
| CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records Dhruv Madhwal, Manan Roy Choudhury, Suparno Roy Chowdhury, Vivek Gupta Published: 2026-09-07Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E19 / R18 (91%) | 15 |
| Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints Ditto PS, Jithin VG Published: 2026-09-07Area: cs.CRCitations: 20 Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E10 / R10 (87%) | 20 |
| Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain Pengyin Shan Published: 2026-09-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E26 / R19 (91%) | - |
| Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing Bin Wu, Guangquan Xu, Weizhe Wang, Xiaoqiang Di Published: 2026-09-07Area: cs.CRCitations: 40 Tags: ai-safety, cscr, preprint | 2026-09-07 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (91%) | 40 |
| Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection Andreas Flatscher, Branka Stojanovi膰, Michael Somma Published: 2026-09-07Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-07 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E9 / R5 (93%) | - |
| AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents Hongyu Sun, Jice Wang, Shangru Zhao, Weizhi Meng Published: 2026-09-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E13 / R11 (91%) | - |
| A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content Jun Dai, Lingyun Zhang, Ping Chen, Xiaoyan Sun Published: 2026-09-06Area: cs.CRCitations: 20 Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (90%) | 20 |
| A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition Yashovardhan Sharma Published: 2026-09-06Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (90%) | 45 |
| AURA-Eval: Evaluation Framework for Acting Under Risk Awareness in LLM Agent Trajectories Aniruddhan Ramesh, Christina-Maria Androna, Chrysoula Zerva, Emmanouil Koukoumidis Published: 2026-09-06Area: cs.CRCitations: 12 Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-09-06 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E8 / R6 (92%) | 12 |
| Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving Rana Abu Bakar Published: 2026-09-06Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E14 / R8 (92%) | 15 |
| Detokenization Leaks: Reconstructing Local LLM Outputs From Cache Traces Benyamin Konstantinov, Eitam Sheetrit, Roy Weiss, Tomer Simon Published: 2026-09-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E11 / R8 (94%) | - |
| Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling Chaoyu Zhang, Heng Jin, Hexuan Yu, Ning Zhang Published: 2026-09-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (90%) | - |
| SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure Chengcheng Wan, Jiangtao Wang, Qi Wang Published: 2026-09-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E14 / R12 (95%) | - |
| WAPP: Safe Learning of Positive Security WAF Policies from Live Traffic Ahmed Saafan, Haitham Ghalwash, Heba Osama, Jana Elfeky Published: 2026-09-06Area: cs.CRCitations: 38 Tags: ai-safety, cscr, preprint | 2026-09-06 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (91%) | 38 |