PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models
Adversarial extraction attacks constitute an insidious threat against Deep Learning (DL) models in-which an adversary aims to steal the architecture, parameters, and hyper-parameters of a targeted DL model. Existing extraction attack literature have observed varying levels of attack success for different DL models and datasets, yet the underlying cause(s) behind their susceptibility often remain unclear, and would help facilitate creating secure DL systems. In this paper we present PINCH: an efficient and automated extraction attack framework capable of designing, deploying, and analyzing extraction attack scenarios across heterogeneous hardware platforms. Using PINCH, we perform extensive experimental evaluation of extraction attacks against 21 model architectures to explore new extraction attack scenarios and further attack staging. Our findings show (1) key extraction characteristics whereby particular model configurations exhibit strong resilience against specific attacks, (2) even partial extraction success enables further staging for other adversarial attacks, and (3) equivalent stolen models uncover differences in expressive power, yet exhibit similar captured knowledge.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackDeep LearningSimilar Papers 제목 키워드 기반
Careful What You Wish For: on the Extraction of Adversarially Trained Models
Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use advers…
Adversarial RobustnessA Kinematic Framework for Screening Candidate Pinch Configurations in Robotic Hand Design without Object or Contact Models
Evaluating the pinch capability of a robotic hand is important for understanding its functional dexterity. However, many existing grasp evaluation methods rely on object geometry or contact force models, which limits the…
Scalable Attribution of Adversarial Attacks via Multi-Task Learning
Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversarial examples. Many works focus on adversar…
Multi-Task LearningModel Extraction and Defenses on Generative Adversarial Networks
Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against genera…
modelModel extractionSeqAttack: On Adversarial Attacks for Named Entity Recognition
Named Entity Recognition is a fundamental task in information extraction and is an essential element for various Natural Language Processing pipelines. Adversarial attacks have been shown to greatly affect the performanc…
Classificationnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+4