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 |
|---|---|---|---|---|---|
| VICBench: A Multi-Language Benchmark for Code Vulnerability Detection Andrew Gacek, Jin Lu, Kevin Luo, Lin Tan Published: 2026-08-12Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-12 | cs.CR | ai-safety, cscr, preprint | - | - |
| A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem Amy Wang, Srinivasan Manoharan, Suraj Kumar Published: 2026-08-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | E15 / R13 (92%) | - |
| Agent Safety Should Be a Runtime Contract Albus W. Ng, Jusheng Zhang, Wenhao Wang, Yi Han Published: 2026-08-11Area: cs.CRCitations: 150 Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | E20 / R18 (89%) | 150 |
| AI Guardrail Survival under Single-Cycle Agentic Self-Summarization Alan Aqrawi, Arian Abbasi, Ted Kwartler Published: 2026-08-11Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | E14 / R8 (90%) | 15 |
| AI Guardrail Survival under Single-Cycle Agentic Self-Summarization Alan Aqrawi, Arian Abbasi, Ted Kwartler Published: 2026-08-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | - | - |
| Backdoor Decontamination Dynamics in LLM Agents Abhay Puri, Alexandre Drouin, Christopher Pal, Gabriel Huang Published: 2026-08-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | - | - |
| On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari Published: 2026-08-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (92%) | - |
| The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark Guannan Wei, Jeremy Spence, Jinhao Zhu, Nicholas Assaderaghi Published: 2026-08-11Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-11 | cs.CR | ai-safety, cscr, preprint | - | - |
| ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Cong Wang, Hongwei Yao, Jieling Chen, Kui Ren Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | - | - |
| ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners Jingzhi Li, Ju Jia, Puyu Zeng, Simeng Qin Published: 2026-08-10Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-10 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference Tejasvi C. Addagada Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | - | - |
| MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulation Jianbing Ni, Jie Cao, Lingshuang Liu, Qi Li Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (92%) | - |
| RangeFactory: Scalable Construction of Multi-Hop Cyber Ranges Ding Li, Hanlin Jiang, Jiandong Jin, Ning Jia Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | - | - |
| STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework Bojia Yu, Ding Li, Hanlin Jiang, Jionghao Huang Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | - | - |
| Stealing Reasoning Traces from Proprietary LLM APIs Alexander Panfilov, Ameya Prabhu, David Schmotz, Ilia Shumailov Published: 2026-08-10Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | - | - |
| Withholding the Completing Chunk: Deterministic Pair-Completion Guardrails for Streaming LLM Output Christopher M. Frost Published: 2026-08-10Area: cs.CRCitations: 14 Tags: ai-safety, cscr, preprint | 2026-08-10 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (92%) | 14 |
| SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills Chi Zhang, Ping Ji, Xinze Chen, Yimin Liu Published: 2026-08-09Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-09 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (90%) | - |
| Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario Satoshi Matsuoka Published: 2026-08-08Area: cs.CRCitations: 47 Tags: ai-safety, cscr, preprint | 2026-08-08 | cs.CR | ai-safety, cscr, preprint | E12 / R9 (88%) | 47 |
| Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection Atsuo Inomata, Kaysarul Anas Apurba, Mahedee Zaman Moon, Md. Hasibul Hasan Published: 2026-08-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-08 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (92%) | - |
| Privacy-Preserving Data Drift Detection and Recovery for Large-Scale LLM Applications via Proxy Representations Eyal Kolman, Haoyu Dong, Josh Ledgard, Michael Levit Published: 2026-08-08Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-08 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (94%) | 15 |
| Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limits Anuj Sharma, Ibne Farabi Shihab, Sanjeda Akter Published: 2026-08-08Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-08 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (92%) | - |
| Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification Bin Benjamin Zhu, Dongmei Zhang, Jin Xuan, Pingyi Hu Published: 2026-08-08Area: cs.CRCitations: 33 Tags: ai-safety, cscr, preprint | 2026-08-08 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (93%) | 33 |
| Adversarial Attacks on Deep OCR Systems Hongzong LI, Jiahao MA, Rong Feng, Shiqin Tang Published: 2026-08-07Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-07 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E9 / R8 (91%) | - |
| HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses Dongyuan Li, Hongxun Gu, Liuyu Xiang, Xiao Zhang Published: 2026-08-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E14 / R7 (91%) | - |
| LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes Doniyorkhon Obidov, Honggang Yu, Kaichen Yang, Xiaolong Guo Published: 2026-08-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (88%) | - |
| Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models Mukesh Singh, Zhuoheng Huang Published: 2026-08-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (93%) | - |
| Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models Mukesh Singh, Zhuoheng Huang Published: 2026-08-07Area: cs.CRCitations: 23 Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (91%) | 23 |
| Soft Redaction of Image Provenance via Zero-Knowledge Proofs John Collomosse, Muhammad Awan Published: 2026-08-07Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E9 / R9 (91%) | - |
| The Anatomy of a Prompt Injection: A Component Model for Structured Analysis Jeremy McHugh Published: 2026-08-07Area: cs.CRCitations: 22 Tags: ai-safety, cscr, preprint | 2026-08-07 | cs.CR | ai-safety, cscr, preprint | E13 / R14 (90%) | 22 |
| ABC: Numerical Data Collection under Local Differential Privacy without Prior Knowledge Hyungbin Kim, Incheol Baek, Yon Dohn Chung Published: 2026-08-06Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-06 | cs.CR | ai-safety, cscr, preprint | E9 / R9 (92%) | - |