Inspect, Understand, Overcome: A Survey of Practical Methods for AI
Safety
- URL: http://arxiv.org/abs/2104.14235v1
- Date: Thu, 29 Apr 2021 09:54:54 GMT
- Title: Inspect, Understand, Overcome: A Survey of Practical Methods for AI
Safety
- Authors: Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas B\"ar, Felix
Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed
Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian
Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan
Kronenberger, Fabian K\"uppers, Jonas L\"ohdefink, Michael Mlynarski, Michael
Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander
Pohl, Varun Ravi-Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan R\"uping,
Timo S\"amann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim
Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian
Wirkert, Tim Wirtz, Matthias Woehrle
- Abstract summary: The use of deep neural networks (DNNs) in safety-critical applications is challenging due to numerous model-inherent shortcomings.
In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged.
Our paper addresses both machine learning experts and safety engineers.
- Score: 54.478842696269304
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The use of deep neural networks (DNNs) in safety-critical applications like
mobile health and autonomous driving is challenging due to numerous
model-inherent shortcomings. These shortcomings are diverse and range from a
lack of generalization over insufficient interpretability to problems with
malicious inputs. Cyber-physical systems employing DNNs are therefore likely to
suffer from safety concerns. In recent years, a zoo of state-of-the-art
techniques aiming to address these safety concerns has emerged. This work
provides a structured and broad overview of them. We first identify categories
of insufficiencies to then describe research activities aiming at their
detection, quantification, or mitigation. Our paper addresses both machine
learning experts and safety engineers: The former ones might profit from the
broad range of machine learning topics covered and discussions on limitations
of recent methods. The latter ones might gain insights into the specifics of
modern ML methods. We moreover hope that our contribution fuels discussions on
desiderata for ML systems and strategies on how to propel existing approaches
accordingly.
Related papers
- Open Problems in Machine Unlearning for AI Safety [61.43515658834902]
Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks.
In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety.
arXiv Detail & Related papers (2025-01-09T03:59:10Z) - Safety Monitoring of Machine Learning Perception Functions: a Survey [7.193217430660011]
New dependability challenges arise when Machine Learning predictions are used in safety-critical applications.
The use of fault tolerance mechanisms, such as safety monitors, is essential to ensure the safe behavior of the system.
This paper presents an extensive literature review on safety monitoring of perception functions using ML in a safety-critical context.
arXiv Detail & Related papers (2024-12-09T10:58:50Z) - Security and Safety Aspects of AI in Industry Applications [0.0]
We summarise issues in the domains of safety and security in machine learning that will affect industry sectors in the next five to ten years.
Reports of underlying problems in both safety and security related domains, for instance adversarial attacks have unsettled early adopters.
The problem for real-world applicability lies in being able to assess the risk of applying these technologies.
arXiv Detail & Related papers (2022-07-16T16:41:00Z) - Practical Machine Learning Safety: A Survey and Primer [81.73857913779534]
Open-world deployment of Machine Learning algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities.
New models and training techniques to reduce generalization error, achieve domain adaptation, and detect outlier examples and adversarial attacks.
Our organization maps state-of-the-art ML techniques to safety strategies in order to enhance the dependability of the ML algorithm from different aspects.
arXiv Detail & Related papers (2021-06-09T05:56:42Z) - Increasing the Confidence of Deep Neural Networks by Coverage Analysis [71.57324258813674]
This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model against different unsafe inputs.
Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs.
arXiv Detail & Related papers (2021-01-28T16:38:26Z) - Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance.
We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems.
We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
arXiv Detail & Related papers (2020-10-19T13:09:31Z) - Security and Machine Learning in the Real World [33.40597438876848]
We build on our experience evaluating the security of a machine learning software product deployed on a large scale to broaden the conversation to include a systems security view of vulnerabilities.
We propose a list of short-term mitigation suggestions that practitioners deploying machine learning modules can use to secure their systems.
arXiv Detail & Related papers (2020-07-13T16:57:12Z) - Adversarial Machine Learning Attacks and Defense Methods in the Cyber
Security Domain [58.30296637276011]
This paper summarizes the latest research on adversarial attacks against security solutions based on machine learning techniques.
It is the first to discuss the unique challenges of implementing end-to-end adversarial attacks in the cyber security domain.
arXiv Detail & Related papers (2020-07-05T18:22:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.