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 |
|---|---|---|---|---|---|
| CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training Amine Lbath, Aurelien Delaitre, Dinesh Manocha, Manan Suri Published: 2026-08-06Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (94%) | 15 |
| Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture Leo Sambrook, Sampo Sovio Published: 2026-08-06Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (93%) | 15 |
| StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection Akbar Rafiey, Avery Ma, Layla El Asri, Leila Pishdad Published: 2026-08-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E13 / R13 (90%) | - |
| When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems Jialuo Chen, Jianan Ma, Jingyi Wang, Lingqi Jiang Published: 2026-08-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | - |
| When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems Jialuo Chen, Jianan Ma, Jingyi Wang, Lingqi Jiang Published: 2026-08-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (90%) | - |
| ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study Arif Hassan Zidan, Bowen Guo, Churan Yu, Haixing Dai Published: 2026-08-05Area: cs.CRCitations: 39 Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-08-05 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E33 / R34 (91%) | 39 |
| Breadcrumbing Search Agents Dacheng Tao, Hanqing Zhao, Kejiang Chen, Nenghai Yu Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | - | - |
| Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework Daqing He, Hongwei Yao, Jiamou Liu, Jincheng An Published: 2026-08-05Area: cs.CRCitations: 33 Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | E11 / R8 (90%) | 33 |
| Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning Chaochao Lu, Tianhang Zheng, Xingyu Zeng, Yuxuan Huang Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | - | - |
| Hardware Design and Security in the Era of Chiplets and LLMs Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz, Ramesh Karri Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | - | - |
| PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates Jingyu Hua, Muzhi Dong, Sheng Zhong, Wei Tong Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | - | - |
| Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic) Armita Kazeminajafabadi, Hyunwoo Oh, Ian Bryant, Mahdi Imani Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (91%) | - |
| When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs Jiaming Cheng, Rajiv Ramnath, Subhransu Das Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | - | - |
| WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking Kejun Zhang, Song Xiao, Yanshuo Zhang, Yuqi Yuan Published: 2026-08-05Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-05 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (88%) | - |
| AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection Jiongchi Yu, Shihao Weng, Xiaofei Xie, Yang Feng Published: 2026-08-04Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (89%) | 45 |
| AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems Ali Dehghantanha, Sajad Homayoun Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | - | - |
| AI Security Leaderboard: Methodology, Results and Minimal Standard Adam Gleave, Dan Zhao, Edward Yee, Grace Cheong Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E9 / R10 (95%) | - |
| AI Security Leaderboard: Methodology, Results and Minimal Standard Adam Gleave, Dan Zhao, Edward Yee, Grace Cheong Published: 2026-08-04Area: cs.CRCitations: 26 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E9 / R10 (95%) | 26 |
| An Inline Control Architecture for Language Models in Intelligent Transportation Systems Mounira Msahli, Narendra Kumar Dewangan Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E10 / R6 (88%) | - |
| A Security-Oriented Lifecycle Model for Large Language Model Systems Eleftherios Batzolis, George Drosatos, Konstantinos Rantos, Vassilis Katsouros Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | - | - |
| Attribute-based Undetectable Watermarking for Generative AI Models Chung-Wei Lee, Er-Cheng Tang, Max Raffel, Miryam Mi-Ying Huang Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | - | - |
| Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills Haoxuan Xu, Mengyuan Li, Peichun Hua Published: 2026-08-04Area: cs.CRCitations: 1 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E6 / R7 (90%) | 1 |
| Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD Amit Shukla, Deepak Singh, Devesh Kumar, Isha Published: 2026-08-04Area: cs.CRCitations: 25 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E14 / R11 (93%) | 25 |
| DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction Hai Wan, Jiabao Gao, Kai Chang, Tian Qiu Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | - | - |
| FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection Delong Ran, Pei Li, Sihan Chen, Tianshuo Cong Published: 2026-08-04Area: cs.CRCitations: 150 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E13 / R15 (93%) | 150 |
| FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks An Khanh Bui, Cong Thanh Nguyen, Diep N. Nguyen, Hoang-Anh Pham Published: 2026-08-04Area: cs.CRCitations: 17 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | 17 |
| Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchain Keisuke Suzuki Published: 2026-08-04Area: cs.CRCitations: 52 Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (94%) | 52 |
| Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents Zhenpeng Li Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (92%) | - |
| SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels Dokyung Song, Euihyun Lee, Jinyoung Park, Yongwan Jo Published: 2026-08-04Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-04 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (91%) | - |
| $S^3$: Improving Agent Safety through Multi-Stage Defense Haoyu Wang, Jun Sun, Zibo Xiao Published: 2026-08-03Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-08-03 | cs.CR | ai-safety, cscr, preprint | E12 / R11 (90%) | 45 |