A general framework for defining and optimizing robustness
Robustness of neural networks has recently attracted a great amount of interest. The many investigations in this area lack a precise common foundation of robustness concepts. Therefore, in this paper, we propose a rigorous and flexible framework for defining different types of robustness properties for classifiers. Our robustness concept is based on postulates that robustness of a classifier should be considered as a property that is independent of accuracy, and that it should be defined in purely mathematical terms without reliance on algorithmic procedures for its measurement. We develop a very general robustness framework that is applicable to any type of classification model, and that encompasses relevant robustness concepts for investigations ranging from safety against adversarial attacks to transferability of models to new domains. For two prototypical, distinct robustness objectives we then propose new learning approaches based on neural network co-training strategies for obtaining image classifiers optimized for these respective objectives.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
Optimizing Collaboration of LLM based Agents for Finite Element Analysis
This paper investigates the interactions between multiple agents within Large Language Models (LLMs) in the context of programming and coding tasks. We utilize the AutoGen framework to facilitate communication among agen…
Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators
Statistical machine learning often uses probabilistic algorithms, such as Markov Chain Monte Carlo (MCMC), to solve a wide range of problems. Probabilistic computations, often considered too slow on conventional processo…
DiagnosticThe Adaptive Arms Race: Redefining Robustness in AI Security
Despite considerable efforts on making them robust, real-world AI-based systems remain vulnerable to decision based attacks, as definitive proofs of their operational robustness have so far proven intractable. Canonical …
The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex
In the supervised binary classification setting, score-oriented losses have been introduced with the aim of optimizing a chosen performance metric directly during the training phase, thus avoiding \textit{a posteriori} t…
Binary ClassificationA Framework for Characterizing Novel Environment Transformations in General Environments
To be robust to surprising developments, an intelligent agent must be able to respond to many different types of unexpected change in the world. To date, there are no general frameworks for defining and characterizing th…