paper-with-me

Papers

Attacking and Defending Machine Learning Applications of Public Cloud

2020-07-27 · Dou Goodman, Hao Xin

Adversarial attack breaks the boundaries of traditional security defense. For adversarial attack and the characteristics of cloud services, we propose Security Development Lifecycle for Machine Learning applications, e.g., SDL for ML. The SDL for ML helps developers build more secure software by reducing the number and severity of vulnerabilities in ML-as-a-service, while reducing development cost.

📄 PDF Abstract BibTeX arXiv:2008.02076

Code (1)

advboxes/AdvBox 공식 구현 tf

Tasks

Adversarial AttackBIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Security Matters: A Survey on Adversarial Machine Learning

2018-10-16 · Guofu Li, Pengjia Zhu, Jin Li, Zhemin Yang 외

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-t…

BIG-bench Machine LearningDeep LearningSurvey

Goal-Oriented Prompt Attack and Safety Evaluation for LLMs

2023-09-21 · Chengyuan Liu, Fubang Zhao, Lizhi Qing, Yangyang Kang 외

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There ar…

Fraternal Twins: Unifying Attacks on Machine Learning and Digital Watermarking

2017-03-16 · Erwin Quiring, Daniel Arp, Konrad Rieck

Machine learning is increasingly used in security-critical applications, such as autonomous driving, face recognition and malware detection. Most learning methods, however, have not been designed with security in mind an…

Autonomous DrivingBIG-bench Machine LearningFace RecognitionMalware Detection+1

FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation

2024-06-03 · Hanlin Gu, Jiahuan Luo, Yan Kang, Yuan YAO 외

Federated learning (FL) has emerged as a collaborative approach that allows multiple clients to jointly learn a machine learning model without sharing their private data. The concern about privacy leakage, albeit demonst…

Deep LearningFederated LearningPrivacy PreservingVertical Federated Learning

Adversarial Attacks on Multi-task Visual Perception for Autonomous Driving

2021-07-15 · Ibrahim Sobh, Ahmed Hamed, Varun Ravi Kumar, Senthil Yogamani

Deep neural networks (DNNs) have accomplished impressive success in various applications, including autonomous driving perception tasks, in recent years. On the other hand, current deep neural networks are easily fooled …

Autonomous DrivingMotion Detectionobject-detectionObject Detection+1