English
Related papers

Related papers: ILION: Deterministic Pre-Execution Safety Gates fo…

200 papers

Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…

Cryptography and Security · Computer Science 2025-08-22 Hengyu An , Jinghuai Zhang , Tianyu Du , Chunyi Zhou , Qingming Li , Tao Lin , Shouling Ji

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

Artificial Intelligence · Computer Science 2026-05-19 Ashwin Aravind

Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…

Cryptography and Security · Computer Science 2026-02-11 Manish Bhattarai , Minh Vu

AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute…

Cryptography and Security · Computer Science 2024-11-26 Edoardo Debenedetti , Jie Zhang , Mislav Balunović , Luca Beurer-Kellner , Marc Fischer , Florian Tramèr

We introduce Orion, a visual agent that integrates vision-based reasoning with tool-augmented execution to achieve powerful, precise, multi-step visual intelligence across images, video, and documents. Unlike traditional vision-language…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 N Dinesh Reddy , Dylan Snyder , Lona Kiragu , Mirajul Mohin , Shahrear Bin Amin , Sudeep Pillai

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency…

Cryptography and Security · Computer Science 2026-03-26 Qianlong Lan , Anuj Kaul

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Cryptography and Security · Computer Science 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

Current AI systems increasingly operate in contexts where their outputs directly trigger real-world actions. Most existing approaches to AI safety, risk management, and governance focus on post-hoc validation, probabilistic risk estimation,…

Artificial Intelligence · Computer Science 2026-04-28 Gadi Lavi

Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically.…

Cryptography and Security · Computer Science 2026-03-11 Yuxu Ge

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…

Artificial Intelligence · Computer Science 2026-05-29 Benlong Wu , Weiming Zhang , Kejiang Chen , Han Fang , Nenghai Yu

Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…

Cryptography and Security · Computer Science 2025-07-10 Tarek Gasmi , Ramzi Guesmi , Ines Belhadj , Jihene Bennaceur

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.…

Cryptography and Security · Computer Science 2026-02-12 Mohan Rajagopalan , Vinay Rao

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…

Software Engineering · Computer Science 2026-04-20 Yining Hong , Yining She , Eunsuk Kang , Christopher S. Timperley , Christian Kästner

Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuarial Action Interface (AAI), a deterministic runtime contract that prices each such action…

Artificial Intelligence · Computer Science 2026-05-26 Hao-Hsuan Chen

AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical for establishing…

Cryptography and Security · Computer Science 2026-04-29 Minghui Xu , Xiaoyu Liu , Yihao Guo , Chunchi Liu , Yue Zhang , Xiuzhen Cheng

As artificial intelligence systems evolve from passive assistants into autonomous agents capable of executing consequential actions, the security boundary shifts from model outputs to tool execution. Traditional security paradigms - log…

Cryptography and Security · Computer Science 2026-02-11 Herman Errico

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense…

Cryptography and Security · Computer Science 2025-12-02 Mintong Kang , Chong Xiang , Sanjay Kariyappa , Chaowei Xiao , Bo Li , Edward Suh

Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web searches, retrieved documents, tool outputs, and user follow-ups, and reasons over them…

Cryptography and Security · Computer Science 2026-05-20 Yash Narendra

Prompt injection constitutes a significant challenge for generative AI systems by inducing unintended outputs. We introduce a multi-agent NLP framework specifically designed to address prompt injection vulnerabilities through layered…

Artificial Intelligence · Computer Science 2025-03-17 Diego Gosmar , Deborah A. Dahl , Dario Gosmar

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…