Security Theater: On the Vulnerability of Classifiers to Exploratory Attacks

03/24/2018
by   Tegjyot Singh Sethi, et al.
0

The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule or signature based methods cannot. However, classifiers operating in adversarial domains are vulnerable to evasion attacks by an adversary, who is capable of learning the behavior of the system by employing intelligently crafted probes. Classification accuracy in such domains provides a false sense of security, as detection can easily be evaded by carefully perturbing the input samples. In this paper, a generic data driven framework is presented, to analyze the vulnerability of classification systems to black box probing based attacks. The framework uses an exploration exploitation based strategy, to understand an adversary's point of view of the attack defense cycle. The adversary assumes a black box model of the defender's classifier and can launch indiscriminate attacks on it, without information of the defender's model type, training data or the domain of application. Experimental evaluation on 10 real world datasets demonstrates that even models having high perceived accuracy (>90 evasion rate (>95 model and empirical evaluation, serve.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/23/2017

Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains

While modern day web applications aim to create impact at the civilizati...
research
07/06/2020

Black-box Adversarial Example Generation with Normalizing Flows

Deep neural network classifiers suffer from adversarial vulnerability: w...
research
10/22/2019

Adversarial Example Detection by Classification for Deep Speech Recognition

Machine Learning systems are vulnerable to adversarial attacks and will ...
research
09/19/2020

EI-MTD:Moving Target Defense for Edge Intelligence against Adversarial Attacks

With the boom of edge intelligence, its vulnerability to adversarial att...
research
10/02/2020

Query complexity of adversarial attacks

Modern machine learning models are typically highly accurate but have be...
research
03/24/2018

A Dynamic-Adversarial Mining Approach to the Security of Machine Learning

Operating in a dynamic real world environment requires a forward thinkin...
research
12/23/2022

Security and Interpretability in Automotive Systems

The lack of any sender authentication mechanism in place makes CAN (Cont...

Please sign up or login with your details

Forgot password? Click here to reset