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 |
|---|---|---|---|---|---|
| Walking the Embedding Space: Datastore Extraction from Multimodal RAG Ali Satvaty, Fatih Turkmen, Maria Carmen Jica, Suzan Verberne Published: 2026-10-01Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-10-01 | cs.CR | ai-safety, cscr, preprint | E9 / R10 (94%) | - |
| ActionGuard: Tool Call Authorization under Poisoned Skills Byung Il Kwak, Jihun Han, Mee Lan Han, Yejin Jang Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses Yang Wang Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry Jiang Xie, Peishuai Sun, Shuhao Li, Tao Yin Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents Duohe Ma, Jun Dai, Kai Chen, Ke Chen Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion Hai Huang, Wentao Chen, Zhen Liang Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| Faithful Dual-constrained Erasure for Robust LLM Safety Alignment Jiaqing Li, Kailong Wang, Shide Zhou, Tianlong Yu Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, alignment-training, cscr, preprint | - | - |
| Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM Agents Jiashu Zhao, Lei Sha, Lingyong Yan, Shuaiqiang Wang Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents Ankit Shah, Arunesh Sinha, Ayan Javeed Shaikh, Nathaniel D. Bastian Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint, safety-evaluation | 2026-09-30 | cs.CR | ai-safety, cscr, preprint, safety-evaluation | E8 / R6 (93%) | - |
| Pretext: Defeating Malicious Skill Detection Frameworks for AI Agents Aritra Dhar, Tobias Kaisar Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| Proof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents Bravish Ghosh Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | E8 / R7 (92%) | - |
| RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination Triage Hang Lyu, Jingtao Zhang, Qibai Chen, Zeming Liu Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs Chuanchao Zang, Jianing Wang, Li Wang, Shanqing Guo Published: 2026-09-30Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-30 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | E12 / R11 (92%) | - |
| Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks Heqing Huang, Rui Lian, Xueyang Tang, Yang Lou Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | - | - |
| Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution Ankit Shah, Harshith Doppalapudi, Nathaniel D. Bastian Published: 2026-09-30Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-30 | cs.CR | ai-safety, cscr, preprint | E10 / R7 (92%) | - |
| Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing Bokun Wang, Daren Zha, Jun Xiao, Miaobo Hu Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E8 / R9 (93%) | - |
| Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning Chaoyu Zhang, Heng Jin, Ning Wang, Shanghao Shi Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E13 / R11 (94%) | - |
| Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback Chu Wang, Genliang Zhu Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (94%) | - |
| Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods Lingzhe Wang, Liyao Xiang, Mingxuan Ma, Tongyang Zhao Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |
| CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition Alexander Zhou, Chen Jason Zhang, Dakun Shen, Di Hong Published: 2026-09-29Area: cs.CRCitations: 15 Tags: ai-safety, alignment-training, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, alignment-training, cscr, preprint | E13 / R11 (93%) | 15 |
| Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injection Longzhu He, Sen Su, XiaoFeng Wang, Xinfeng Li Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |
| Controlled Decoding Attacks on Black-Box LLMs Charith Peris, Franck Dernoncourt, Jesson Wang, Ryan A. Rossi Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |
| CounterSteer: Suppressing Indirect Prompt Injection with Activation Steering Mark Russinovich Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |
| Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks Balaji Palanisamy, Xiaowei Jia, Ying Song Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |
| Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue Hadi Masoudi, Minghong Fang, Omar Sheta, Rinku Deuja Published: 2026-09-29Area: cs.CRCitations: - Tags: adversarial-robustness, ai-safety, cscr, preprint | 2026-09-29 | cs.CR | adversarial-robustness, ai-safety, cscr, preprint | - | - |
| Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks Abby D'Cruz, Alexandra Souly, Kai Fronsdal, Robert Kirk Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (94%) | - |
| Forensic-Aware Continual Adaptation for Image Forgery Localization Alex C. Kot, Anwei Luo, Chenqi Kong, Peisong He Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E11 / R10 (94%) | - |
| Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs Mustafa Arslan Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E8 / R6 (91%) | - |
| LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems John Stankovic, Meiyi Ma, Ziyan An Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | E7 / R6 (92%) | - |
| Making Duplicate Reimbursement Unrepresentable: A Verified Ethereum E-Invoice System for Humans and AI Agents Jia Cai Published: 2026-09-29Area: cs.CRCitations: - Tags: ai-safety, cscr, preprint | 2026-09-29 | cs.CR | ai-safety, cscr, preprint | - | - |