Lower bounds on the robustness to adversarial perturbations

By Jonathan Peck, Joris Roels, Bart Goossens, Yvan Saeys. 2017

69 citations recorded by the source corpus.

Subfields: Scaling & Learning Theory, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Scaling & Learning Theory

In Safety, Robustness & Interpretability

Citations in the corpus

Certified Robustness to Adversarial Examples with Differential Privacy (2018, background): “Another line of work focuses on finding conservative bounds on the number of robustness violations [48], [57].”
Efficient Formal Safety Analysis of Neural Networks (2018, background): “Similarly, existing work on finding lower bounds on the L-norms of adversarial perturbations that can fool a neural network also suffer from the same limitations [22, 31].”
Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks (2018, methodology): “While prior work required separate analysis for slightly different components [29, 24, 7, 26], we provide a more unified analysis.”
Adversarial vulnerability for any classifier (2018, methodology): “Other works have recently studied procedures and algorithms to provably guarantee a certain level of robustness [22, 23, 24, 25, 26], and have been applied to small datasets (e.”
Efficient Neural Network Robustness Certification with General Activation Functions (2018, background): “Some analytical lower bounds based on operator norms on the weight matrices [3] or the Jacobian matrix in NNs [17] do not exploit special property of ReLU and thus can be very loose [20].”
Towards Robust Deep Neural Networks with BANG (2016, background): “This fundamental problem of deep learning has recently received increasing attention by researchers [3, 8, 21].”
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for L0 Norm (2018, background): “We also mention [19], which computes a lower bound of local robustness for the L 2 norm by propagating relations between layers backward from the output.”