English
Related papers

Related papers: When Flatness Does (Not) Guarantee Adversarial Rob…

200 papers

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

This paper proposes a theoretical framework to evaluate and compare the performance of stochastic gradient algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments. Previous works have…

Machine Learning · Computer Science 2025-07-03 Ying Cao , Zhaoxian Wu , Kun Yuan , Ali H. Sayed

Deep neural networks (DNNs) have gained prominence in various applications, such as classification, recognition, and prediction, prompting increased scrutiny of their properties. A fundamental attribute of traditional DNNs is their…

Machine Learning · Computer Science 2023-08-15 Roman Garaev , Bader Rasheed , Adil Khan

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

Machine Learning · Computer Science 2020-10-23 Akhilan Boopathy , Sijia Liu , Gaoyuan Zhang , Cynthia Liu , Pin-Yu Chen , Shiyu Chang , Luca Daniel

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Machine Learning · Computer Science 2023-06-14 Omar Montasser

Adversarial perturbations are imperceptible changes to input pixels that can change the prediction of deep learning models. Learned weights of models robust to such perturbations are previously found to be transferable across different…

Machine Learning · Computer Science 2020-10-30 Alvin Chan , Yi Tay , Yew-Soon Ong

One of the major concerns for neural network training is that the non-convexity of the associated loss functions may cause bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what…

Machine Learning · Computer Science 2023-07-19 Ruoyu Sun , Dawei Li , Shiyu Liang , Tian Ding , R Srikant

Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of…

Machine Learning · Computer Science 2017-03-27 Nicholas Cheney , Martin Schrimpf , Gabriel Kreiman

Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the training loss, and thus a…

Machine Learning · Computer Science 2023-07-25 Kaiyue Wen , Zhiyuan Li , Tengyu Ma

It is broadly known that deep neural networks are susceptible to being fooled by adversarial examples with perturbations imperceptible by humans. Various defenses have been proposed to improve adversarial robustness, among which adversarial…

Machine Learning · Computer Science 2023-03-30 Wei Wei , Jiahuan Zhou , Ying Wu

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code…

Machine Learning · Computer Science 2022-08-23 Goutham Ramakrishnan , Jordan Henkel , Zi Wang , Aws Albarghouthi , Somesh Jha , Thomas Reps

The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that…

Machine Learning · Computer Science 2021-06-28 Sadia Chowdhury , Ruth Urner

The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that…

Machine Learning · Computer Science 2026-05-29 Amir Mehrpanah , Matteo Gamba , Hossein Azizpour

Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories; gradient masking, robust optimization, and adversarial…

Machine Learning · Computer Science 2019-10-24 Leslie N. Smith

Representational sparsity is known to affect robustness to input perturbations in deep neural networks (DNNs), but less is known about how the semantic content of representations affects robustness. Class selectivity-the variability of a…

Machine Learning · Computer Science 2021-03-31 Matthew L. Leavitt , Ari Morcos

Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…

Machine Learning · Computer Science 2020-12-07 Adam Noack , Isaac Ahern , Dejing Dou , Boyang Li

The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient…

Disordered Systems and Neural Networks · Physics 2022-02-15 Carlo Baldassi , Clarissa Lauditi , Enrico M. Malatesta , Gabriele Perugini , Riccardo Zecchina

Neural networks are getting better accuracy with higher energy and computational cost. After quantization, the cost can be greatly saved, and the quantized models are more hardware friendly with acceptable accuracy loss. On the other hand,…

Machine Learning · Computer Science 2021-10-26 Chang Song , Riya Ranjan , Hai Li

We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approaches do not provide…

Machine Learning · Computer Science 2025-11-11 Peter Blohm , Patrick Indri , Thomas Gärtner , Sagar Malhotra

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 generation. This process…

Machine Learning · Computer Science 2019-03-26 Tommaso Dreossi , Shromona Ghosh , Alberto Sangiovanni-Vincentelli , Sanjit A. Seshia