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 |
|---|---|---|---|---|---|
| PatchBench: Evaluating AI Agents for Vulnerability Patching Aastha Mahajan, Chihao Shen, Jeffery Siyuan Tian, Jiacheng Li Published: 2026-09-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-03 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (92%) | - |
| Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface ABM Shawkat Ali, Adrita Rahman Tory, Khondokar Fida Hasan, Md Abu Layek Published: 2026-09-03Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-03 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (93%) | - |
| Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection Arman Zharmagambetov, David Wagner, Ivan Evtimov, Kamalika Chaudhuri Published: 2026-09-03Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-03 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | 15 |
| SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations Center Cassie L. Cagwin, David J. Wild, Uday Vallabhaneni Published: 2026-09-03Area: cs.CRCitations: 18 Tags: ai-safety, cscr, preprint | 2026-09-03 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | 18 |
| Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning Dong Liu, Eric Hanchen Jiang, Jinxi Yu, Kai-Wei Chang Published: 2026-09-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-02 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (93%) | - |
| PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generation Bradford Campbell, Jiechao Gao, Jie Wang, Michael Lepech Published: 2026-09-02Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-09-02 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (90%) | 15 |
| Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics Chin-Chen Chang, Ching-Chun Chang, Hui Li, Isao Echizen Published: 2026-09-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-02 | cs.CR | ai-safety, cscr, preprint | E9 / R10 (92%) | - |
| When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization Haozhang Li, Junzheng Shi, Mi Zhou, Xinjie Lin Published: 2026-09-02Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-02 | cs.CR | ai-safety, cscr, preprint | E6 / R6 (93%) | - |
| Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents Christoph Siebenbrunner, Laurent Bindschaedler, Quentin Botha Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (93%) | - |
| Agent Memory Is a Surface for Endogenous Authorization Laundering Ansel Kaplan Erol, Mika Okamoto, Tommaso Cerruti Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (94%) | - |
| Bonded Recourse for Smart-Contract Settlement of Compensable Agent Side Effects Christoph Siebenbrunner, Laurent Bindschaedler, Quentin Botha Published: 2026-09-01Area: cs.CRCitations: 13 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (91%) | 13 |
| Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents Dianbo Sui, Jing Shao, Lijun Li, Xiaofang Yang Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (93%) | - |
| Differentially Private Paired Table-Image Multimodal Synthesis Josephine Lamp, Kai Chen, Somesh Jha, Tianhao Wang Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E7 / R5 (92%) | - |
| HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation Alessandro Zirilli, Davide Marincione, Emanuele Rodol脿, Evgenios M. Kornaropoulos Published: 2026-09-01Area: cs.CRCitations: 26 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (95%) | 26 |
| HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation Evgeniy Kokuykin, Nikita Oblakov, Sabrina Sadiekh Published: 2026-09-01Area: cs.CRCitations: 15 Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-01 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E15 / R11 (93%) | 15 |
| MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence Walid Saidi Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (91%) | - |
| Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling Alessandro Biondi, Giulio Rossolini, Stefano Leggio Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (93%) | - |
| Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis Chong Yu, Justin Zhan, Tianyu Jiang, Yagna Manasa Boyapati Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (94%) | - |
| Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study Arpan Kumar Mahapatra Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (95%) | - |
| Ranked by the Matcher: A Reproducibility Audit of Knowledge Graph Extraction from Threat Reports Houbing Herbert Song, Safayat Bin Hakim Published: 2026-09-01Area: cs.CRCitations: 49 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (91%) | 49 |
| SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems Junjie Xu, Neil Fendley, Rui Yang, Yang Hong Published: 2026-09-01Area: cs.CRCitations: 197 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E17 / R17 (94%) | 197 |
| The Safeguard Worked. Is the LLM System Safer? Nenghai Yu, Pingyu Wu, Weiming Zhang Published: 2026-09-01Area: cs.CRCitations: 229 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E11 / R7 (95%) | 229 |
| When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning Haixu Tang, Siyuan Zhang, Xiaofeng Wang, Xiaoyi Chen Published: 2026-09-01Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, alignment-training, cscr, preprint | E9 / R7 (92%) | - |
| Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges Cong Liu, Guoping Hu, Jing Shao, Junhua Liu Published: 2026-09-01Area: cs.CRCitations: 38 Tags: ai-safety, cscr, preprint | 2026-09-01 | cs.CR | ai-safety, cscr, preprint | E15 / R12 (93%) | 38 |
| Capability-Gated Language Models: Security Composes, Utility Does Not Augustas Ma膷ijauskas, Laurynas Lopata, Patrikas Vanagas Published: 2026-08-31Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (91%) | 45 |
| Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems Jyotirmoy Sundi, Panduranga Sai Varma Dantuluri Published: 2026-08-31Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | E13 / R11 (93%) | - |
| Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective Alberto Giaretta, Andrea Agiollo, Marco Antonio Corallo, Mauro Conti Published: 2026-08-31Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (93%) | - |
| SingProbe Technical Report Sing Team Published: 2026-08-31Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | - | - |
| SIR: Self-improving Red-teaming for Compute Use Agents Chen Xiong, Pin-Yu Chen, Stjepan Picek, Tsung-Yi Ho Published: 2026-08-31Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (91%) | - |
| Workload Identification with Physical Side Channels for AI Governance Gabriel Kulp, Simone Gargiulo Published: 2026-08-31Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-31 | cs.CR | ai-safety, cscr, preprint | E8 / R5 (91%) | 15 |