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 |
|---|---|---|---|---|---|
| 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 |
| A Formal Analysis of Agent Payment Protocols Cong Wang, Jianyu Niu, Ke Jiang, Mohan Yu Published: 2026-08-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-30 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (94%) | - |
| Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents Ismail Hossain, Md Jahangir Alam, Sai Puppala, Sajedul Talukder Published: 2026-08-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-30 | cs.CR | ai-safety, cscr, preprint | E9 / R8 (90%) | - |
| Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection Lei Xu, Rabimba Karanjai, Weidong Shi, Wujie Xiong Published: 2026-08-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-30 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (94%) | - |
| Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap Ashok Subbabhatta Gopalakrishna Published: 2026-08-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-30 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (93%) | - |
| Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding Kejia Zhang, Tianyuan Zou, Yang Liu, Zixuan GU Published: 2026-08-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-29 | cs.CR | ai-safety, cscr, preprint | E9 / R7 (93%) | - |
| Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation Hector Espinos-Morato, Johanna Angulo, V铆ctor Yeste Published: 2026-08-29Area: cs.CRCitations: 45 Tags: ai-safety, cscr, preprint | 2026-08-29 | cs.CR | ai-safety, cscr, preprint | E12 / R14 (94%) | 45 |
| Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs Eunna Lee, Heonjin Ha, Jamin Jung, Jungpyo Nam Published: 2026-08-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-29 | cs.CR | ai-safety, cscr, preprint | E10 / R5 (94%) | - |
| Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback Cong Wang, Dahui Li, Guanlong Wu, Jianyu Niu Published: 2026-08-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-29 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (95%) | - |
| CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks? Haibo Hu, Minxin Du, Qingqing Ye, Xiaoyu Xu Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | E10 / R8 (91%) | - |
| Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-as-Code Animesh Shaw Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | E14 / R10 (92%) | - |
| ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools Neil Gong, Patrick Li, Peinian Li, Ruiqi Wang Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | E6 / R5 (90%) | - |
| FISGuard: Defending Against Membership Inference via Fixed Input Subspaces Haocheng Jiang, Hua Shen Published: 2026-08-28Area: cs.CRCitations: 30 Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (91%) | 30 |
| Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers Abrar Alotaibi, Moataz Ahmed, Muhammad Shahid Jabbar, Sadam Al-Azani Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | - | - |
| LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment Haipeng Cai, Jiawei Guo, Jingjing Nie, Krishna Meda Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | - | - |
| LongPIBench: A Long-Context Benchmark for Prompt Injection Jinyuan Jia, Neil Zhenqiang Gong, Yupei Liu, Yuqi Jia Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | - | - |
| Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification Cameron Wilding, Fatemeh Ganji, Mina Shaker Published: 2026-08-28Area: cs.CRCitations: 25 Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-28 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E8 / R7 (95%) | 25 |
| Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification Cameron Wilding, Fatemeh Ganji, Mina Shaker Published: 2026-08-28Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-28 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E8 / R7 (95%) | - |
| Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach Adil Alshammari, Hayretdin Bahsi Published: 2026-08-28Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-28 | cs.CR | ai-safety, cscr, preprint | E11 / R9 (96%) | - |
| Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers April Xu, Owen Cox, Weiyu Xu Published: 2026-08-28Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-08-28 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| Beyond F1: Evaluating Coverage and Failure Recovery in AI Model Security Scanners Anuj Kaul, Indranil Sanyal, Qianlong Lan, Vinothini Pandurangan Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E8 / R8 (93%) | - |
| Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction Chia-Mu Yu, Ci-Yang Tsai, Muxi Lyu, Raluca Ada Popa Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (91%) | - |
| PLCBench: Can Autonomous LLM Agents Turn PLC Access into Sustained Physical Impact? Haoming Liu, Jingyu Zheng, Lichao Wu, Linkang Du Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (90%) | - |
| RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution Changsheng Chen, Haoliang Li, Hui Liu, Junjie Zhang Published: 2026-08-27Area: cs.CRCitations: 15 Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E13 / R12 (90%) | 15 |
| Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Bin Chong, Chenhao Wu, Chongyang Zhang, Haoxuan Jia Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E27 / R20 (94%) | - |
| Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Bin Chong, Chenhao Wu, Chongyang Zhang, Haoxuan Jia Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E20 / R17 (93%) | - |
| Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents Bin Chong, Chenhao Wu, Chongyang Zhang, Haoxuan Jia Published: 2026-08-27Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E27 / R20 (95%) | - |
| Semantic Watermarking with Order-Robust Detection over Sub-sentence Units Abdulrahman Diaa, Florian Kerschbaum, Jonathan Petit Published: 2026-08-27Area: cs.CRCitations: 49 Tags: ai-safety, cscr, preprint | 2026-08-27 | cs.CR | ai-safety, cscr, preprint | E10 / R9 (94%) | 49 |