paper-with-me

Papers

Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?

2024-12-19 · Mario Fritz

General Purpose AI - such as Large Language Models (LLMs) - have seen rapid deployment in a wide range of use cases. Most surprisingly, they have have made their way from plain language models, to chat-bots, all the way to an almost ``operating system''-like status that can control decisions and logic of an application. Tool-use, Microsoft co-pilot/office integration, and OpenAIs Altera are just a few examples of increased autonomy, data access, and execution capabilities. These methods come with a range of cybersecurity challenges. We highlight some of the work we have done in terms of evaluation as well as outline future opportunities and challenges.

📄 PDF Abstract BibTeX arXiv:2501.01435

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Effective Mitigations for Systemic Risks from General-Purpose AI

2024-11-14 · Risto Uuk, Annemieke Brouwer, Tim Schreier, Noemi Dreksler 외

The systemic risks posed by general-purpose AI models are a growing concern, yet the effectiveness of mitigations remains underexplored. Previous research has proposed frameworks for risk mitigation, but has left gaps in…

Model evaluation for extreme risks

2023-05-24 · Toby Shevlane, Sebastian Farquhar, Ben Garfinkel, Mary Phuong 외

Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such…

model

Toward Reliable, Safe, and Secure LLMs for Scientific Applications

2026-03-18 · Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi Mallick arxiv

As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trust…

Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems

2024-10-30 · Rokas Gipiškis, Ayrton San Joaquin, Ze Shen Chin, Adrian Regenfuß 외

There is an urgent need to identify both short and long-term risks from newly emerging types of Artificial Intelligence (AI), as well as available risk management measures. In response, and to support global efforts in r…

DescriptiveManagement

A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics

2025-05-19 · Takeshi Kojima, Yaonan Zhu, Yusuke Iwasawa, Toshinori Kitamura 외

Recent Foundation Model-enabled robotics (FMRs) display greatly improved general-purpose skills, enabling more adaptable automation than conventional robotics. Their ability to handle diverse tasks thus creates new oppor…

Survey