Reliability and accuracy of iris biometric modality has
prompted its large-scale deployment for critical applications
such as border control and national ID projects. The
extensive growth of iris recognition systems has raised apprehensions
about susceptibility of these systems to various
attacks. In the past, researchers have examined the impact
of various iris presentation attacks such as textured contact
lenses and print attacks. In this research, we present a novel
presentation attack using deep learning based synthetic iris
generation. Utilizing the generative capability of deep convolutional
generative adversarial networks and iris quality
metrics, we propose a new framework, named as iDCGAN
(iris deep convolutional generative adversarial network) for
generating realistic appearing synthetic iris images. We
demonstrate the effect of these synthetically generated iris
images as presentation attack on iris recognition by using
a commercial system. The state-of-the-art presentation attack
detection framework, DESIST is utilized to analyze if it
can discriminate these synthetically generated iris images
from real images. The experimental results illustrate that
mitigating the proposed synthetic presentation attack is of
paramount importance.
more »
« less
Greedy Attack and Gumbel Attack: Generating Adversarial Examples on Discrete Data
We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalable learning-based method, Gumbel Attack, that illustrate various tradeoffs in the design of attacks. We demonstrate the effectiveness of these methods using both quantitative metrics and human evaluation on various stateof-the-art models for text classification, including a word-based CNN, a character-based CNN and an LSTM. As an example of our results, we show that the accuracy of character-based convolutional networks drops to the level of random selection by modifying only five characters through Greedy Attack.
more »
« less
- Award ID(s):
- 1914917
- PAR ID:
- 10464456
- Date Published:
- Journal Name:
- Journal of machine learning research
- Volume:
- 21
- ISSN:
- 1532-4435
- Page Range / eLocation ID:
- 1-36
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool deep learning models by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. We further propose attack methods based on genetic algorithms and gradient descent in the scenario where additional prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers.more » « less
-
null (Ed.)Spurious power consumption data reported from compromised meters controlled by organized adversaries in the Advanced Metering Infrastructure (AMI) may have drastic consequences on a smart grid’s operations. While existing research on data falsification in smart grids mostly defends against isolated electricity theft, we introduce a taxonomy of various data falsification attack types, when smart meters are compromised by organized or strategic rivals. To counter these attacks, we first propose a coarse-grained and a fine-grained anomaly-based security event detection technique that uses indicators such as deviation and directional change in the time series of the proposed anomaly detection metrics to indicate: (i) occurrence, (ii) type of attack, and (iii) attack strategy used, collectively known as attack context . Leveraging the attack context information, we propose three attack response metrics to the inferred attack context: (a) an unbiased mean indicating a robust location parameter; (b) a median absolute deviation indicating a robust scale parameter; and (c) an attack probability time ratio metric indicating the active time horizon of attacks. Subsequently, we propose a trust scoring model based on Kullback-Leibler (KL) divergence, that embeds the appropriate unbiased mean, the median absolute deviation, and the attack probability ratio metric at runtime to produce trust scores for each smart meter. These trust scores help classify compromised smart meters from the non-compromised ones. The embedding of the attack context, into the trust scoring model, facilitates accurate and rapid classification of compromised meters, even under large fractions of compromised meters, generalize across various attack strategies and margins of false data. Using real datasets collected from two different AMIs, experimental results show that our proposed framework has a high true positive detection rate, while the average false alarm and missed detection rates are much lesser than 10% for most attack combinations for two different real AMI micro-grid datasets. Finally, we also establish fundamental theoretical limits of the proposed method, which will help assess the applicability of our method to other domains.more » « less
-
Trajectory prediction forecasts nearby agents’ moves based on their historical trajectories. Accurate trajectory prediction (or prediction in short) is crucial for autonomous vehicles (AVs). Existing attacks compromise the prediction model of a victim AV by directly manipulating the historical trajectory of an attacker AV, which has limited real-world applicability. This paper, for the first time, explores an indirect attack approach that induces prediction errors via attacks against the perception module of a victim AV. Although it has been shown that physically realizable attacks against LiDAR-based perception are possible by placing a few objects at strategic locations, it is still an open challenge to find an object location from the vast search space in order to launch effective attacks against prediction under varying victim AV velocities. Through analysis, we observe that a prediction model is prone to an attack focusing on a single point in the scene. Consequently, we propose a novel two-stage attack framework to realize the single-point attack. The first stage of predictionside attack efficiently identifies, guided by the distribution of detection results under object-based attacks against perception, the state perturbations for the prediction model that are effective and velocity-insensitive. In the second stage of location matching, we match the feasible object locations with the found state perturbations. Our evaluation using a public autonomous driving dataset shows that our attack causes a collision rate of up to 63% and various hazardous responses of the victim AV. The effectiveness of our attack is also demonstrated on a real testbed car 1. To the best of our knowledge, this study is the first security analysis spanning from LiDARbased perception to prediction in autonomous driving, leading to a realistic attack on prediction. To counteract the proposed attack, potential defenses are discussed.more » « less
-
First responders and other tactical teams rely on mo- bile tactical networks to coordinate and accomplish emergent time- critical tasks. The information exchanged through these networks is vulnerable to various strategic cyber network attacks. Detecting and mitigating them is a challenging problem due to the volatile and mobile nature of an ad hoc environment. This paper proposes MalCAD, a graph machine learning-based framework for detecting cyber attacks in mobile tactical software-defined networks. Mal- CAD operates based on observing connectivity features among various nodes obtained using graph theory, instead of collecting information at each node. The MalCAD framework is based on the XGBOOST classification algorithm and is evaluated for lost versus wasted connectivity and random versus targeted cyber attacks. Results show that, while the initial cyber attacks create a loss of 30%–60% throughput, MalCAD results in a gain of average throughput by 25%–50%, demonstrating successful attack mitigation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
