中文
相关论文

相关论文: Parallax: Why AI Agents That Think Must Never Act

200 篇论文

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures…

人工智能 · 计算机科学 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime guardrails, training-time alignment, and post-hoc auditing…

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,…

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

密码学与安全 · 计算机科学 2026-02-12 Mohan Rajagopalan , Vinay Rao

The rapid evolution of autonomous, agentic artificial intelligence within financial services has introduced an existential architectural crisis: large language models (LLMs) are probabilistic, non-deterministic systems operating in domains…

计算机科学中的逻辑 · 计算机科学 2026-04-03 Devakh Rashie , Veda Rashi

Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…

AI agents that interact with their environments through tools enable powerful applications, but in high-stakes business settings, unintended actions can cause unacceptable harm, such as privacy breaches and financial loss. Existing…

软件工程 · 计算机科学 2026-04-20 Yining Hong , Yining She , Eunsuk Kang , Christopher S. Timperley , Christian Kästner

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

密码学与安全 · 计算机科学 2026-04-28 Richard Joseph Mitchell

As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures are falsely advertised. To address the threat, we propose…

密码学与安全 · 计算机科学 2026-03-09 Xisen Jin , Michael Duan , Qin Lin , Aaron Chan , Zhenglun Chen , Junyi Du , Xiang Ren

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

人工智能 · 计算机科学 2026-05-12 Royce Moon , Lav R. Varshney

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

人工智能 · 计算机科学 2026-05-07 Chenglin Yang

As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design…

计算与语言 · 计算机科学 2025-11-10 Gauri Kholkar , Ratinder Ahuja

Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…

密码学与安全 · 计算机科学 2025-11-21 Badrinath Ramakrishnan , Akshaya Balaji

Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates…

密码学与安全 · 计算机科学 2025-10-02 Dalal Alharthi , Ivan Roberto Kawaminami Garcia

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…

密码学与安全 · 计算机科学 2025-03-04 Ishaan Domkundwar , Mukunda N S , Ishaan Bhola , Riddhik Kochhar

The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - introduces a class of safety risk not addressed by existing…

人工智能 · 计算机科学 2026-03-17 Florin Adrian Chitan

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful…

人工智能 · 计算机科学 2026-05-20 Ravi Pandya , Madison Bland , Duy P. Nguyen , Changliu Liu , Jaime Fernández Fisac , Andrea Bajcsy

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

密码学与安全 · 计算机科学 2026-04-09 Hongyi Lu , Nian Liu , Shuai Wang , Fengwei Zhang

Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are highly vulnerable to indirect prompt injection attacks, where…

密码学与安全 · 计算机科学 2026-01-16 Hao Li , Yankai Yang , G. Edward Suh , Ning Zhang , Chaowei Xiao

Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…

密码学与安全 · 计算机科学 2025-11-25 Itay Hazan , Yael Mathov , Guy Shtar , Ron Bitton , Itsik Mantin
‹ 上一页 1 2 3 10 下一页 ›