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 |
|---|---|---|---|---|---|
| MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication Hankai Liu, Jinghan Xu, Longze Fan, Xinjin Li Published: 2026-08-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-03 | cs.CR | ai-safety, cscr, preprint | - | - |
| MutMem: Cryptographically Authorized Mutation in Persistent Agent Memory Walid Saidi Published: 2026-08-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-03 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (95%) | - |
| Privacy-Preserving AI Verification via Minimal Information Disclosure Gabriel Kulp, Sleem Abdelghafar Published: 2026-08-03Area: cs.CRCitations: 55 Tags: ai-safety, cscr, preprint | 2026-08-03 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (90%) | 55 |
| Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach Mohamed Chahine Ghanem Published: 2026-08-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-03 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (93%) | - |
| An AI Approach to Verified Production Cryptographic Libraries Chuyue Sun, Clark Barrett, David L. Dill, Haoze Wu Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | - | - |
| CallScreenBench: Benchmarking On-Device Models as Phone Secretaries Simiao Ren Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | - | - |
| Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks Haoyu Zhang, Mohammad Zandsalimy, Shanu Sushmita, Shibo Zheng Published: 2026-08-02Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-02 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial Abay Zhurekbay, Fan Li, Tao Liu Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | E13 / R12 (89%) | - |
| Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks Chao Wu, Cheng Ji, Chuancheng Shi, Fei Shen Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, alignment-training, cscr, preprint | E12 / R11 (91%) | - |
| Neuro-Symbolic Participation Governance for Verifiable AI Agents in Open Digital Twin Ecosystems Juan Li, Wei Cai, Yan Bai Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | - | - |
| Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments Dotan Davidovich, Hai Rozencwajg, Or Hiltch, Yair Amar Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-08-02 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E10 / R9 (91%) | - |
| Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation Diego Kreutz, Francis Luis Santos Vargas, Rodrigo Brand茫o Mansilha Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-08-02 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E12 / R6 (94%) | - |
| Vulnerabilities, Secrets and Misconfiguration in the Highest-Exposure Docker Hub Images Beatriz Machado, Cristhian Kapelinski, Diego Kreutz Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | E12 / R14 (93%) | - |
| Why Formal Monitors Fail: Attack Distribution Entropy as a Coverage Bound for LTL-Based LLM Agent Safety Ruiyang Zhang Published: 2026-08-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-02 | cs.CR | ai-safety, cscr, preprint | - | - |
| Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures Faisal Haque Bappy, Kamrul Hasan, Raiful Hasan, Tahrim Hossain Published: 2026-08-01Area: cs.CRCitations: 21 Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-01 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E14 / R12 (91%) | 21 |
| A False Average: Chain-of-Thought Monitors Collapse Where They Are the Only Defense Leo Richter, Shikhar Shiromani Published: 2026-08-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | - |
| Auditable Release Control for Pedagogical Leakage in LLM Tutors Nizam Kadir Published: 2026-08-01Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (91%) | 45 |
| From Chasing Ghosts to Missed Attacks: Perspectives and Perceptions of SOC Practitioners on LLM Integration, Risks, and Readiness Alena Naiakshina, Fabian Ising, Jonas Thurner, Lea Groeber Published: 2026-08-01Area: cs.CRCitations: 59 Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (92%) | 59 |
| Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor Anyu Wang, Jinyuan Liu, Pei Li, Tianrui Wang Published: 2026-08-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E13 / R11 (90%) | - |
| Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms Ch Prathima, Kishor Kumar Gajula, M Anjan Kumar Published: 2026-08-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (89%) | - |
| Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity Jiaxi Wen, Junwei Yao, Lai Yun Choi, Wenbo Ye Published: 2026-08-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E15 / R8 (89%) | - |
| Supporting Cybersecurity Risk Management for Medical Devices via the SECUMAN Ontology and Shapes Anne Esslinger, Evi Hartig, Hannes Strass, Lia Kacholdt Published: 2026-08-01Area: cs.CRCitations: 68 Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (91%) | 68 |
| Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure Han Qiu, Jianshuo Dong, Jie Zhang, Maosen Zhang Published: 2026-08-01Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (95%) | 15 |
| ZK-SR117: A Chunked Zero-Knowledge Attestation Design for Aggregated Fair-Lending Metrics, with a Control Mapping toward Full SR 11-7 Coverage Asaduzzaman Anik, Eklachur Rahman Bhuiyan, Mohammad Nasir Uddin, Rahnuma Tabassum Orpita Published: 2026-08-01Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-01 | cs.CR | ai-safety, cscr, preprint | E12 / R10 (94%) | 15 |
| Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale Nicol谩s Padilla Published: 2026-07-31Area: cs.CRCitations: 20 Tags: ai-safety, cscr, preprint | 2026-07-31 | cs.CR | ai-safety, cscr, preprint | E38 / R37 (86%) | 20 |
| Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory Hankai Liu, Jinghan Xu, Wanru Shao, Xinjin Li Published: 2026-07-31Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-07-31 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | 15 |
| MOSAIC: Masked Outsourcing of Secure AI Computations James Hsin-yu Chiang, Kari Kostiainen, Sheila Zingg, Srdjan Capkun Published: 2026-07-31Area: cs.CRCitations: 34 Tags: ai-safety, cscr, preprint | 2026-07-31 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (91%) | 34 |
| Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking Guangming Shi, Hao Hu, Ping Zhang, Xubo Li Published: 2026-07-31Area: cs.CRCitations: 35 Tags: ai-safety, cscr, preprint | 2026-07-31 | cs.CR | ai-safety, cscr, preprint | E7 / R7 (92%) | 35 |
| Symbolic Attack Chain Generation from Atomic Red Team Techniques: An Empirical Study of Predicate Representation Granularity Ramya Varunsegar Published: 2026-07-31Area: cs.CRCitations: 18 Tags: ai-safety, cscr, preprint | 2026-07-31 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (92%) | 18 |
| Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks Haralampos-G. Stratigopoulos, Spyridon Raptis Published: 2026-07-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-07-30 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (92%) | - |