ISP Reading Group

ISP Reading Group

MQ ISP Reading Group

Purpose/Time and Venue/

To inform our ongoing (and future) research, in this weekly reading group, we will critically review and discuss cornerstone security and privacy papers from top-notch security and privacy conferences/journals (i.e., IEEE Security and Privacy (Oakland), USENIX Security, CCS, NDSS, IMC, WWW, PETS, IEEE TIFS, ACM TOPS).

The ISP Reading Group meets Thursday from 12:00pm - 1:00pm (fortnightly); Level 2, 4 Research Park Drive (BD Building)

Suggested Papers

Machine Learning (e.g., GAN, ML for solving Security and Privacy issues)
  1. Schönherr et al., Adversarial Attacks Against ASR Systems via Psychoacoustic Hiding, NDSS’18
  2. Tramer et al., Stealing Machine Learning Models via Prediction APIs, Usenix Sec’16
  3. Pihur, V., Korolova, A., Liu, F., Sankuratripati, S., Yung, M., Huang, D., & Zeng, R. (2018). Differentially-Private “Draw and Discard" Machine Learning.
  4. Nasr, M., Shokri, R., & Houmansadr, A. (2018, October). Machine learning with membership privacy using adversarial regularization.ACM SIGSAC.https://arxiv.org/pdf/1807.05852.pdf
  5. Hunt, T., Zhu, Z., Xu, Y., Peter, S., & Witchel, E. (2018). Ryoan: A distributed sandbox for untrusted computation on secret data. ACM Transactions on Computer Systems (TOCS). Usenix’16. https://www.cs.utexas.edu/users/witchel/pubs/hunt16osdi-ryoan.pdf
  6. Hunt, T., Song, C., Shokri, R., Shmatikov, V., & Witchel, E. (2018). Chiron: Privacy-preserving machine learning as a service. https://arxiv.org/pdf/1803.05961.pdf
  7. Salem, A., Zhang, Y., Humbert, M., Fritz, M., & Backes, M. Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv 2018 https://arxiv.org/pdf/1806.01246.pdf
  8. Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V.. Exploiting unintended feature leakage in collaborative learning. IEEE’2018
  9. ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models https://arxiv.org/pdf/1806.01246.pdf
  10. LOGAN: Membership Inference Attacks Against Generative Models https://www.degruyter.com/downloadpdf/j/popets.2019.2019.issue-1/popets-2019-0008/popets-2019-0008.pdf
Web and Apps
  1. Ayers et al., The Price of Free Illegal Live Streaming Services, https://arxiv.org/abs/1901.00579, 2018
  2. Rajab et al., The Nacebo Effect on the Web: An Analysis of Fake Anti-Virus Distribution, LEET’10
  3. Degeling et al., We value your privacy -- Now take some Cookies: Measuring the GPDR’s impact on Web Privacy, NDSS’19
  4. Urban et al., The Unwanted Sharing Economy: An Analysis of Cookie Syncing and User Transparency under GDPR, https://arxiv.org/pdf/1811.08660.pdf, 2018.
  5. Mutchler et al., A large-scale study of mobile web app security, MOST'15
  6. Roesner et al., Securing embedded user interfaces: Android and beyond, Usenix Sec'13
  7. Das, A., et.al.. (2018, October). The Web's Sixth Sense: A Study of Scripts Accessing Smartphone Sensors. ACM.https://dl.acm.org/citation.cfm?id=3243860
  8. Staicu, C. A., & Pradel, M. Leaky Images: Targeted Privacy Attacks in the Web.http://software-lab.org/publications/usenixSec2019.pdf
Security and Privacy
  1. Ling, X., Ji, S., Zou, J., Wang, J., Wu, C., Li, B., & Wang, T. Deepsec: A uniform platform for security analysis of deep learning model. IEEE S&P’2019 http://cse.unl.edu/~qyan/courses/CSCE-990/Papers/P10-2.pdf
  2. Ding, S. H., Fung, B. C., & Charland, P. Asm2vec: Boosting static representation robustness for binary clone search against code obfuscation and compiler optimization. In Asm2Vec. IEEE’2019
  3. Wang, B., Yao, Y., Shan, S., Li, H., Viswanath, B., Zheng, H., & Zhao, B. Y. Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks. IEEE. https://people.cs.vt.edu/vbimal/publications/backdoor-sp19.pdf
  4. Li, J., Ji, S., Du, T., Li, B., & Wang, T.. TextBugger: Generating Adversarial Text Against Real-world Applications. arXiv 2018 https://arxiv.org/pdf/1812.05271.pdf
Distributed Database/ Data Management
  1. Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets https://arxiv.org/abs/1902.03785

Discussed Papers 2019

DatePaper Title, Author, LinkPresenter
14 Feb 

Das, A., et.al.. (2018, October). The Web's Sixth Sense: A Study of Scripts Accessing Smartphone Sensors. ACM. https://dl.acm.org/citation.cfm?id=3243860

Muhammad Ikram
28 Feb 

Schönherr, L., et.al. (2018). Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding. https://arxiv.org/pdf/1808.05665.pdf

Ben Zhao
14 Mar 

Song, W., et al. (2018). DeepMem: Learning Graph Neural Network Models for Fast and Robust Memory Forensic Analysis. https://dl.acm.org/citation.cfm?id=3243813

Kevin Hoarau
28 Mar Ling, X., Ji, S., Zou, J., Wang, J., Wu, C., Li, B., & Wang, T. Deepsec: A uniform platform for security analysis of deep learning model. http://cse.unl.edu/~qyan/courses/CSCE-990/Papers/P10-2.pdf Mahmood Yousefiazar
11 April 

Wang, B., Yao, Y., Shan, S., Li, H., Viswanath, B., Zheng, H., & Zhao, B. Y. Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks. IEEE. https://people.cs.vt.edu/vbimal/publications/backdoor-sp19.pdf

Jason Xue
9 May 

Drynx: Decentralized, Secure, Verifiable System for Statistical Queries and Machine Learning on Distributed Datasets https://arxiv.org/abs/1902.03785

Marina Dehez Clementi
23 May 

A Billion Open Interfaces for Eve and Mallory: MitM, DoS, and Tracking Attacks on iOS and macOS Through Apple Wireless Direct Link https://www.usenix.org/system/files/sec19fall_stute_prepub.pdf

Muhammad Ikram
06 Jun Nasr, M., Shokri, R., & Houmansadr, A. Machine learning with membership privacy using adversarial regularization. https://arxiv.org/pdf/1807.05852.pdfShakila M Tonni
20 Jun 

LOGAN: Membership Inference Attacks Against Generative Models https://www.degruyter.com/downloadpdf/j/popets.2019.2019.issue-1/popets-2019-0008/popets-2019-0008.pdf

Nazim Uddin Sheikh
04 July 

A decade of mal-activity reporting: a retrospective analysis of internet malicious activity blacklists. https://arxiv.org/pdf/1904.10629.pdf

Ben Zhao
18 July 

DaDiDroid: An Obfuscation Resilient Tool for Detecting Android Malware via Weighted Directed Call Graph Modelling https://imikr4m.github.io/paper/SECRYPT_2019_21_CR.pdf

 
1 Aug 

Olympus: Sensor Privacy through Utility Aware Obfuscation https://users.cs.duke.edu/~ashwin/pubs/OLYMPUS-PoPETS2019-final.pdf

Rahat Masood
15 Aug 

1) Own accepted work: When Air Traffic Management Meets Blockchain Technology: a Blockchain-based concept for securing the sharing of Flight Data https://hal-enac.archives-ouvertes.fr/hal-02181089/

2) Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams https://arxiv.org/pdf/1710.00811.pdf

Marina Clementi

Tahiry Rabehaja
29 Aug

Helen: Maliciously Secure Coopetitive Learning for LinearModels https://arxiv.org/pdf/1907.07212.pdf

Tham Nguyen
 

Own accepted work:  A Longitudinal Analysis of Online Ad-Blocking Blacklists https://arxiv.org/abs/1906.00166

F-BLEAU: Fast Black-box Leakage Estimation https://arxiv.org/pdf/1902.01350.pdf

Saad Hashmi

Nan Wu
10 Oct

On Inferring Training Data Attributes in Machine Learning Models https://arxiv.org/abs/1908.10558

Aviral Agrawal
24 Oct

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment Link:https://arxiv.org/pdf/1902.08552.pdf

Gioacchino Tangari

Link to all presented slides

Back to the top of this page