中文
相关论文

相关论文: Ambient Persuasion in a Deployed AI Agent: Unautho…

200 篇论文

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

计算机与社会 · 计算机科学 2025-08-21 Carson Ezell , Xavier Roberts-Gaal , Alan Chan

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…

计算机与社会 · 计算机科学 2025-12-02 K. J. Kevin Feng , Tae Soo Kim , Rock Yuren Pang , Faria Huq , Tal August , Amy X. Zhang

Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

密码学与安全 · 计算机科学 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

Deploying agentic AI in regulated contexts requires principled reasoning about two design dimensions: agency (what the system can do) and autonomy (how much it acts without human involvement). Though often treated independently, they are…

人工智能 · 计算机科学 2026-05-13 Damir Safin , Dian Balta

Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is exposed to user…

人工智能 · 计算机科学 2026-05-22 Hyejun Jeong , Amir Houmansadr , Shlomo Zilberstein , Eugene Bagdasarian

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 autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

人工智能 · 计算机科学 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

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…

密码学与安全 · 计算机科学 2026-04-01 Chong Xiang , Drew Zagieboylo , Shaona Ghosh , Sanjay Kariyappa , Kai Greshake , Hanshen Xiao , Chaowei Xiao , G. Edward Suh

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

机器学习 · 计算机科学 2026-04-07 Ninghui Li , Kaiyuan Zhang , Kyle Polley , Jerry Ma

When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or ethical constraints, they can resort to unsanctioned behaviour. Existing inference time safety…

密码学与安全 · 计算机科学 2026-05-01 Francesca Gomez

We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week…

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…

密码学与安全 · 计算机科学 2026-05-08 Hao Li , Ruoyao Wen , Shanghao Shi , Ning Zhang , Yevgeniy Vorobeychik , Chaowei Xiao

Human decision-making is strongly influenced by cognitive biases, particularly under conditions of uncertainty and risk. While prior work has examined bias in single-step decisions with immediate outcomes and in human interaction with a…

人机交互 · 计算机科学 2026-03-25 Teerthaa Parakh , Karen M. Feigh

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

密码学与安全 · 计算机科学 2026-03-17 Simone Aonzo , Merve Sahin , Aurélien Francillon , Daniele Perito

AI systems are increasingly intertwined with daily life, assisting users with various tasks and guiding decision-making. This integration introduces risks of AI-driven manipulation, where such systems may exploit users' cognitive biases and…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

密码学与安全 · 计算机科学 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's…

人工智能 · 计算机科学 2022-12-29 Tim Johnson , Nick Obradovich
‹ 上一页 1 2 3 10 下一页 ›