Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples
Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with high confidence in the prediction. In this work, we propose a general framework based on the perturbation analysis of learning algorithms which consists of convex programming and is able to recover many current adversarial attacks as special cases. The framework can be used to propose novel attacks against learning algorithms for classification and regression tasks under various new constraints with closed form solutions in many instances. In particular we derive new attacks against classification algorithms which are shown to achieve comparable performances to notable existing attacks. The framework is then used to generate adversarial perturbations for regression tasks which include single pixel and single subset attacks. By applying this method to autoencoding and image colorization tasks, it is shown that adversarial perturbations can effectively perturb the output of regression tasks as well.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationColorizationGeneral ClassificationImage ColorizationregressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Formalization of Robustness for Deep Neural Networks
Deep neural networks have been shown to lack robustness to small input perturbations. The process of generating the perturbations that expose the lack of robustness of neural networks is known as adversarial input genera…
Adversarial AttackUnifying Generative Models with GFlowNets and Beyond
There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models…
Decision MakingA Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes
Parametric policy search algorithms are one of the methods of choice for the optimisation of Markov Decision Processes, with Expectation Maximisation and natural gradient ascent being considered the current state of the …
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective
The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing thes…
Data PoisoningOn the Stability of Neural Networks in Deep Learning
Deep learning has achieved remarkable success across a wide range of tasks, but its models often suffer from instability and vulnerability: small changes to the input may drastically affect predictions, while optimizatio…
Adversarial Robustness