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 |
|---|---|---|---|---|---|
| AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions Aishan Liu, Dacheng Tao, Jiakai Wang, Jinyang Guo Published: 2025-06-17Area: Agent SafetyCitations: 13 Tags: adversarial-robustness, agent-safety, ai-safety, benchmark | 2025-06-17 | Agent Safety | adversarial-robustness, agent-safety, ai-safety, benchmark | E5 / R4 (99%) | 13 |
| OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents Agatha Duzan, Francesco Croce, Hao Zhao, Maksym Andriushchenko Published: 2025-06-17Area: Agent SafetyCitations: 29 Tags: agent-safety, ai-safety, benchmark | 2025-06-17 | Agent Safety | agent-safety, ai-safety, benchmark | E6 / R3 (95%) | 29 |
| SHADE Arena: Sabotage Monitoring for LLM Agents Buck Shlegeris, Chen Bo Calvin Zhang, Henry Sleight, Joe Benton Published: 2025-06-17Area: Agent SafetyCitations: 18 Tags: agent-safety, ai-safety, benchmark | 2025-06-17 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R4 (95%) | 18 |
| Context manipulation attacks: Web agents are susceptible to corrupted memory Ashwin Hebbar, Atharv Singh Patlan, Pramod Viswanath, Prateek Mittal Published: 2025-06-18Area: Agent SafetyCitations: 4 Tags: agent-safety, ai-safety, empirical | 2025-06-18 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R3 (95%) | 4 |
| A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures Changting Lin, Chaochao Chen, Dezhang Kong, Hujin Peng Published: 2025-06-24Area: Agent SafetyCitations: 35 Tags: agent-safety, ai-safety, survey | 2025-06-24 | Agent Safety | agent-safety, ai-safety, survey | E5 / R3 (97%) | 35 |
| A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents Chang Liu, Hang Su, Jun Luo, Jun Zhu Published: 2025-06-30Area: Agent SafetyCitations: 12 Tags: agent-safety, ai-safety, survey | 2025-06-30 | Agent Safety | agent-safety, ai-safety, survey | E5 / R3 (95%) | 12 |
| Enhancing LLM Agent Safety via Causal Influence Prompting Dongyoon Hahm, June Suk Choi, Kimin Lee, Sungsoo Ahn Published: 2025-07-01Area: Agent SafetyCitations: 1 Tags: agent-safety, ai-safety, empirical | 2025-07-01 | Agent Safety | agent-safety, ai-safety, empirical | E6 / R4 (99%) | 1 |
| SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents Aishan Liu, Ee-Chien Chang, Jinyuan He, Siyuan Liang Published: 2025-07-01Area: Agent SafetyCitations: 5 Tags: adversarial-robustness, agent-safety, ai-safety, empirical, safety-evaluation | 2025-07-01 | Agent Safety | adversarial-robustness, agent-safety, ai-safety, empirical, safety-evaluation | E5 / R4 (95%) | 5 |
| Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms Ines Belhadj, Jihene Bennaceur, Ramzi Guesmi, Tarek Gasmi Published: 2025-07-08Area: Agent SafetyCitations: 4 Tags: agent-safety, ai-safety, empirical | 2025-07-08 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R3 (94%) | 4 |
| OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety Aditya Bharat Soni, Graham Neubig, Maarten Sap, Nouha Dziri Published: 2025-07-08Area: Agent SafetyCitations: 13 Tags: agent-safety, ai-safety, benchmark | 2025-07-08 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (95%) | 13 |
| Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm Ari Juels, Bill Marino Published: 2025-07-11Area: Agent SafetyCitations: 2 Tags: agent-safety, ai-safety, position | 2025-07-11 | Agent Safety | agent-safety, ai-safety, position | E6 / R3 (96%) | 2 |
| WebGuard: Building a Generalizable Guardrail for Web Agents Boyuan Zheng, Dawn Song, Huan Sun, Michael Lin Published: 2025-07-18Area: Agent SafetyCitations: 7 Tags: agent-safety, ai-safety, dataset | 2025-07-18 | Agent Safety | agent-safety, ai-safety, dataset | E4 / R3 (95%) | 7 |
| Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition Alexander Grattan, Andy Zou, Ayla Croft, Dan Hendrycks Published: 2025-07-28Area: Agent SafetyCitations: 10 Tags: agent-safety, ai-safety, benchmark | 2025-07-28 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (98%) | 10 |
| Measuring Harmfulness of Computer-Using Agents Aaron Xuxiang Tian, Janet Tang, Jiaxin Wen, Ruofan Zhang Published: 2025-07-31Area: Agent SafetyCitations: 1 Tags: agent-safety, ai-safety, benchmark | 2025-07-31 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (97%) | 1 |
| Searching for Privacy Risks in LLM Agents via Simulation Diyi Yang, Yanzhe Zhang Published: 2025-08-14Area: Agent SafetyCitations: 8 Tags: agent-safety, ai-safety, empirical | 2025-08-14 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R4 (91%) | 8 |
| Systematic Analysis of MCP Security Peng Di, Puzhuo Liu, Sheng Wen, Wanlun Ma Published: 2025-08-18Area: Agent SafetyCitations: 17 Tags: agent-safety, ai-safety, benchmark | 2025-08-18 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (96%) | 17 |
| Incident Analysis for AI Agents Alan Chan, Carson Ezell, Xavier Roberts-Gaal Published: 2025-08-19Area: Agent SafetyCitations: 2 Tags: agent-safety, ai-safety, theoretical | 2025-08-19 | Agent Safety | agent-safety, ai-safety, theoretical | E5 / R3 (91%) | 2 |
| LM Agents May Fail to Act on Their Own Risk Knowledge Chris J. Maddison, Elizabeth Li, Honghua Dong, Tianxiao Li Published: 2025-08-19Area: Agent SafetyCitations: - Tags: agent-safety, ai-safety, empirical | 2025-08-19 | Agent Safety | agent-safety, ai-safety, empirical | E6 / R4 (95%) | - |
| MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers Guanquan Shi, Haifeng Sun, Haohua Du, Haoran Cheng Published: 2025-08-19Area: Agent SafetyCitations: 17 Tags: agent-safety, ai-safety, benchmark | 2025-08-19 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (96%) | 17 |
| Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation Dongyoon Hahm, Kimin Lee, Taywon Min, Woogyeol Jin Published: 2025-08-19Area: Agent SafetyCitations: 7 Tags: agent-safety, ai-safety, alignment-training, empirical | 2025-08-19 | Agent Safety | agent-safety, ai-safety, alignment-training, empirical | E5 / R3 (94%) | 7 |
| Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills David Noever Published: 2025-08-27Area: Agent SafetyCitations: - Tags: adversarial-robustness, agent-safety, ai-safety, empirical | 2025-08-27 | Agent Safety | adversarial-robustness, agent-safety, ai-safety, empirical | E5 / R3 (93%) | - |
| MindGuard: Tracking, Detecting, and Attributing MCP Tool Poisoning Attack via Decision Dependence Graph Guanquan Shi, Haohua Du, HaoRan Cheng, Junyang Zhang Published: 2025-08-28Area: Agent SafetyCitations: 2 Tags: agent-safety, ai-safety, empirical | 2025-08-28 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R3 (97%) | 2 |
| Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes Abhijnan Nath, Carine Graff, Nikhil Krishnaswamy Published: 2025-09-07Area: Agent SafetyCitations: 2 Tags: agent-safety, ai-safety, alignment-training, empirical | 2025-09-07 | Agent Safety | agent-safety, ai-safety, alignment-training, empirical | E5 / R3 (94%) | 2 |
| Mind Your Server: A Systematic Study of Parasitic Toolchain Attacks on the MCP Ecosystem Libo Chen, Qinsheng Hou, Shenghong Li, Shuli Zhao Published: 2025-09-08Area: Agent SafetyCitations: 6 Tags: agent-safety, ai-safety, empirical | 2025-09-08 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R3 (96%) | 6 |
| SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Haifeng Wang, Hongfei Xiao, Hongru Wang, Qian Yu Published: 2025-09-09Area: Agent SafetyCitations: 1 Tags: agent-safety, ai-safety, benchmark, safety-evaluation | 2025-09-09 | Agent Safety | agent-safety, ai-safety, benchmark, safety-evaluation | E4 / R3 (94%) | 1 |
| Regulating the Agency of LLM-based Agents Joshua Joseph, Se谩n Boddy Published: 2025-09-25Area: Agent SafetyCitations: - Tags: agent-safety, ai-safety, position | 2025-09-25 | Agent Safety | agent-safety, ai-safety, position | E5 / R3 (95%) | - |
| AI Kill Switch for Malicious Web-based LLM Agents Sangdon Park, Sechan Lee Published: 2025-09-26Area: Agent SafetyCitations: - Tags: agent-safety, ai-safety, empirical | 2025-09-26 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R4 (96%) | - |
| SafeSearch: Automated Red-Teaming for the Safety of LLM-Based Search Agents Han Qiu, Hao Wang, Jianshuo Dong, Ke Xu Published: 2025-09-28Area: Agent SafetyCitations: - Tags: agent-safety, ai-safety, benchmark | 2025-09-28 | Agent Safety | agent-safety, ai-safety, benchmark | E5 / R3 (94%) | - |
| Dive into the Agent Matrix: A Realistic Evaluation of Self-Replication Risk in LLM Agents Boxuan Zhang, Jiaxuan Guo, Jing Shao, Yi Yu Published: 2025-09-29Area: Agent SafetyCitations: 1 Tags: agent-safety, ai-safety, empirical, safety-evaluation | 2025-09-29 | Agent Safety | agent-safety, ai-safety, empirical, safety-evaluation | E6 / R3 (95%) | 1 |
| Takedown: How It's Done in Modern Coding Agent Exploits Donghyeon Kim, Eunkyu Lee, Insu Yun, Wonyoung Kim Published: 2025-09-29Area: Agent SafetyCitations: 2 Tags: agent-safety, ai-safety, empirical | 2025-09-29 | Agent Safety | agent-safety, ai-safety, empirical | E5 / R3 (93%) | 2 |