Shiqing Ma (Purdue University), Yingqi Liu (Purdue University), Guanhong Tao (Purdue University), Wen-Chuan Lee (Purdue University), Xiangyu Zhang (Purdue University)

Deep Neural Networks (DNN) are vulnerable to adversarial samples that
are generated by perturbing correctly classified inputs to cause DNN
models to misbehave (e.g., misclassification). This can potentially
lead to disastrous consequences especially in security-sensitive
applications. Existing defense and detection techniques work well for
specific attacks under various assumptions (e.g., the set of possible
attacks are known beforehand). However, they are not sufficiently
general to protect against a broader range of attacks. In this paper,
we analyze the internals of DNN models under various attacks and
identify two common exploitation channels: the provenance channel and
the activation value distribution channel. We then propose a novel
technique to extract DNN invariants and use them to perform runtime
adversarial sample detection. Our experimental results of 11 different
kinds of attacks on popular datasets including ImageNet and 13 models
show that our technique can effectively detect all these attacks
(over 90% accuracy) with limited false positives. We also compare it
with three state-of-the-art techniques including the Local Intrinsic
Dimensionality (LID) based method, denoiser based methods (i.e.,
MagNet and HGD), and the prediction inconsistency based approach
(i.e., feature squeezing). Our experiments show promising results.

View More Papers

CodeAlchemist: Semantics-Aware Code Generation to Find Vulnerabilities in JavaScript...

HyungSeok Han (KAIST), DongHyeon Oh (KAIST), Sang Kil Cha (KAIST)

Read More

MBeacon: Privacy-Preserving Beacons for DNA Methylation Data

Inken Hagestedt (CISPA Helmholtz Center for Information Security), Yang Zhang (CISPA Helmholtz Center for Information Security), Mathias Humbert (Swiss Data Science Center, ETH Zurich/EPFL), Pascal Berrang (CISPA Helmholtz Center for Information Security), Haixu Tang (Indiana University Bloomington), XiaoFeng Wang (Indiana University Bloomington), Michael Backes (CISPA Helmholtz Center for Information Security)

Read More

A Treasury System for Cryptocurrencies: Enabling Better Collaborative Intelligence

Bingsheng Zhang (Lancaster University), Roman Oliynykov (IOHK Ltd.), Hamed Balogun (Lancaster University)

Read More

Profit: Detecting and Quantifying Side Channels in Networked Applications

Nicolás Rosner (University of California, Santa Barbara), Ismet Burak Kadron (University of California, Santa Barbara), Lucas Bang (Harvey Mudd College), Tevfik Bultan (University of California, Santa Barbara)

Read More