paper-with-me

홈 › Papers

AI Risk Management Should Incorporate Both Safety and Security

2024-05-29 · Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal

The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security. Although the two disciplines now come together under the overarching goal of AI risk management, they have historically evolved separately, giving rise to differing perspectives. Therefore, in this paper, we advocate that stakeholders in AI risk management should be aware of the nuances, synergies, and interplay between safety and security, and unambiguously take into account the perspectives of both disciplines in order to devise mostly effective and holistic risk mitigation approaches. Unfortunately, this vision is often obfuscated, as the definitions of the basic concepts of "safety" and "security" themselves are often inconsistent and lack consensus across communities. With AI risk management being increasingly cross-disciplinary, this issue is particularly salient. In light of this conceptual challenge, we introduce a unified reference framework to clarify the differences and interplay between AI safety and AI security, aiming to facilitate a shared understanding and effective collaboration across communities.

📄 PDF Abstract BibTeX arXiv:2405.19524

Code (0)

등록된 구현이 없습니다.

Tasks

Management

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Affirmative safety: An approach to risk management for high-risk AI

2024-04-14 · Akash R. Wasil, Joshua Clymer, David Krueger, Emily Dardaman 외

Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on th…

Management

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management

2025-02-10 · Simeon Campos, Henry Papadatos, Fabien Roger, Chloé Touzet 외

The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack…

ManagementRed Teaming

Risk Management Core -- Towards an Explicit Representation of Risk in Automated Driving

2023-02-15 · Nayel Fabian Salem, Thomas Kirschbaum, Marcus Nolte, Christian Lalitsch-Schneider 외

While current automotive safety standards provide implicit guidance on how unreasonable risk can be avoided, manufacturers are required to specify risk acceptance criteria for Automated Driving Systems (SAE Level 3 and h…

Management

Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics for Urban Transportation Management

2024-07-03 · Tao Li, Zilin Bian, Haozhe Lei, Fan Zuo 외

Traditional mobility management strategies emphasize macro-level mobility oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digi…

Management

From nuclear safety to LLM security: Applying non-probabilistic risk management strategies to build safe and secure LLM-powered systems

2025-05-20 · Alexander Gutfraind, Vicki Bier

Large language models (LLMs) offer unprecedented and growing capabilities, but also introduce complex safety and security challenges that resist conventional risk management. While conventional probabilistic risk analysi…

Management