English
Related papers

Related papers: Owner-Harm: A Missing Threat Model for AI Agent Sa…

200 papers

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges…

Artificial Intelligence · Computer Science 2026-05-19 Chenning Li , Pan Hu , Justin Xu , Baris Ozbas , Olivia Liu , Caroline Van , Manxue Li , Wei Zhou , Mohammad Alizadeh , Pengyu Zhang , KK Sriramadhesikan , Ming Zhang

As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to…

Cryptography and Security · Computer Science 2025-10-28 Madhur Jindal , Hari Shrawgi , Parag Agrawal , Sandipan Dandapat

As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating deployment-specific risks. We present a comprehensive, observability-driven workflow: we…

Computation and Language · Computer Science 2026-04-28 Ilham Wicaksono , Zekun Wu , Rahul Patel , Theo King , Adriano Koshiyama , Philip Treleaven

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…

Artificial Intelligence · Computer Science 2025-10-03 Arman Zharmagambetov , Chuan Guo , Ivan Evtimov , Maya Pavlova , Ruslan Salakhutdinov , Kamalika Chaudhuri

Autonomous agents powered by Large Language Models (LLMs) acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for…

Cryptography and Security · Computer Science 2026-05-15 Xinyu Liu , Yukai Zhao , Xing Hu , Xin Xia

Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…

Artificial Intelligence · Computer Science 2026-02-20 Xinhao Deng , Jiaqing Wu , Miao Chen , Yue Xiao , Ke Xu , Qi Li

Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing…

Computers and Society · Computer Science 2025-12-12 Malcolm Murray , Steve Barrett , Henry Papadatos , Otter Quarks , Matt Smith , Alejandro Tlaie Boria , Chloé Touzet , Siméon Campos

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…

Artificial Intelligence · Computer Science 2026-02-26 Akshat Naik , Jay Culligan , Yarin Gal , Philip Torr , Rahaf Aljundi , Alasdair Paren , Adel Bibi

AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…

Cryptography and Security · Computer Science 2025-03-04 Ishaan Domkundwar , Mukunda N S , Ishaan Bhola , Riddhik Kochhar

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

Cryptography and Security · Computer Science 2025-12-30 Armstrong Foundjem , Lionel Nganyewou Tidjon , Leuson Da Silva , Foutse Khomh

Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…

Cryptography and Security · Computer Science 2026-03-09 Yuxuan Qiao , Dongqin Liu , Hongchang Yang , Wei Zhou , Songlin Hu

AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…

Cryptography and Security · Computer Science 2026-03-25 Zhun Wang , Tianneng Shi , Jingxuan He , Matthew Cai , Jialin Zhang , Dawn Song

Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…

Computation and Language · Computer Science 2026-01-01 Srija Mukhopadhyay , Sathwik Reddy , Shruthi Muthukumar , Jisun An , Ponnurangam Kumaraguru

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…

Cryptography and Security · Computer Science 2026-02-13 Aashish Kolluri , Rishi Sharma , Manuel Costa , Boris Köpf , Tobias Nießen , Mark Russinovich , Shruti Tople , Santiago Zanella-Béguelin

Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to…

Artificial Intelligence · Computer Science 2026-05-06 Wenyue Hua , Tianyi Peng , Chi Wang , Jiaxin Pei , Ian Kaufman , Bryan Lim , Chandler Fang

The performance of large language model (LLM) agents depends critically on the execution harness, the system layer that orchestrates tool use, context management, and state persistence. Yet this same architectural centrality makes the…

Cryptography and Security · Computer Science 2026-05-12 Xixun Lin , Yang Liu , Yancheng Chen , Yongxuan Wu , Yucheng Ning , Yilong Liu , Nan Sun , Shun Zhang , Bin Chong , Chuan Zhou , Yanan Cao

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a…

Computation and Language · Computer Science 2026-01-27 Chen Chen , Kim Young Il , Yuan Yang , Wenhao Su , Yilin Zhang , Xueluan Gong , Qian Wang , Yongsen Zheng , Ziyao Liu , Kwok-Yan Lam

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

Artificial Intelligence · Computer Science 2026-04-06 Yunhao Feng , Yifan Ding , Yingshui Tan , Xingjun Ma , Yige Li , Yutao Wu , Yifeng Gao , Kun Zhai , Yanming Guo

Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in…

Cryptography and Security · Computer Science 2025-12-18 Viet K. Nguyen , Mohammad I. Husain