A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Securely trains neural networks remotely with deep learning's flaws.
Secure sum outperforms homomorphic encryption in collaborative deep learning.
This paper discusses adversarial attacks on cyber security systems using machine learning.
The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods however are susceptible to security attacks. The adversaries can exploit the tra…
Since the inception of Deep Reinforcement Learning (DRL) algorithms, there has been a growing interest in both research and industrial communities in the promising potentials of this paradigm. The list of current and envisioned applications of deep RL ranges from autonomous navigation and robotics to control applicatio…
The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive, and scalable. Machine learning, or more specifically deep reinforcement learning…
Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While sev…
End-to-end learning of codes for secure BPSK communication in Gaussian wiretap channel.
secml is a Python library for secure and explainable machine learning.
The future Internet of Things (IoT) will have a deep economical, commercial and social impact on our lives. The participating nodes in IoT networks are usually resource-constrained, which makes them luring targets for cyber attacks. In this regard, extensive efforts have been made to address the security and privacy is…
This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.
We develop a secure aggregation protocol for federated learning that reduces communication and computation costs.
To assure cyber security of an enterprise, typically SIEM (Security Information and Event Management) system is in place to normalize security event from different preventive technologies and flag alerts. Analysts in the security operation center (SOC) investigate the alerts to decide if it is truly malicious or not. H…
The paper addresses challenges in edge deep learning for IoT, proposing new directions.
New attack method improves neural network security.
We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs …
Survey on securing ML for healthcare, addressing privacy and robustness issues.
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descen…
Deep learning identifies unknown IoT devices in network traffic.
Deep-Lock secures DNN models with secret keys.
Paper proposes scalable privacy-preserving DNN for industrial applications.
Paper proposes NeuroAttack to undermine SNNs security through bit-flips.
A novel model combines deep learning and extreme value theory for multivariate cyber risk prediction.
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of …
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that can compromise its integrity and efficiency. Security attacks can be divided bas…
FedGRU uses federated learning to predict traffic flow accurately while preserving user privacy.
Proposes a new method to improve deep model security against adversarial deformations.
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a range of mission-critical deep learning systems and applications. This paper ta…
Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an atta…
CHEETAH speeds up secure MLaaS by 100x over fastest existing schemes.
DUPLE tackles cross-deployment recognition in fiber-optic perimeter security with meta-learning.
Recently, image forensics community has paied attention to the research on the design of effective algorithms based on deep learning technology and facts proved that combining the domain knowledge of image forensics and deep learning would achieve more robust and better performance than the traditional schemes. Instead…
Deep learning detects arrhythmia from RR-interval ECG data.
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model. In this paper, we propose new secure architectures that guarantee preservation of data privacy, trustworthy sequence of iterative learning and equ…
Secure submodel learning protects privacy in federated learning.
Study introduces UEBA framework using Deep Autoencoders for anomaly detection.
Deep RL agent secures 2nd place in CityLearn Challenge for district demand management.
Stochastic defense improves natural classifiers against adversarial attacks.
Differential privacy improves AI security, fairness, and learning.
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from re…
GTA is the first backdoor attack on GNNs, demonstrating vulnerabilities in graph-oriented security models.
Cyber security has grown up to be a hot issue in recent years. How to identify potential malware becomes a challenging task. To tackle this challenge, we adopt deep learning approaches and perform flow detection on real data. However, real data often encounters an issue of imbalanced data distribution which will lead t…
Defense against small image patches using occlusions.
Deep-CAPTCHA cracks visual CAPTCHAs using deep learning.
Paper analyzes InstaHide's security, recovering all private images with provable guarantee.
We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep learning methods of federated learning, split learning and large batch stochastic gr…
New method speeds up training of deep networks robust to adversarial attacks.