PhD CyberSeminars

Speaker: Prof. Vitaly Shmatikov

Affiliation: Cornell Tech, USA

Date: Dec 14, 2022

Time: 16.30

Location: Aula Magna, Edificio C, Viale Regina Elena 295

Abstract: Modern machine learning models achieve super-human accuracy on tasks such as image classification and natural-language generation, but accuracy does not tell the entire story of what these models are learning. In this talk, I will look at today's machine learning from a security and privacy perspective, and ask several fundamental questions. Could models trained on sensitive private data memorize and leak this data? When training involves crowd-sourced data, untrusted users, or third-party code, could models learn malicious functionality, causing them to produce incorrect or biased outputs? What damage could result from such compromised models?

I will illustrate these vulnerabilities with concrete examples and discuss the benefits and tradeoffs of technologies (such as federated learning) that promise to protect the integrity and privacy of machine learning models and their training data. I will then outline practical approaches towards making trusted machine learning a reality.

Bio: Vitaly Shmatikov is a professor of computer science at Cornell Tech, where he works on computer security and privacy. Vitaly's research team has received the PET Award for Outstanding Research in Privacy Enhancing Technologies three times, as well as multiple Distinguished Paper and Test-of-Time Awards from the IEEE Symposium on Security and Privacy, USENIX Security Symposium, and the ACM Conference on Computer and Communications Security. Prior to joining Cornell, Vitaly worked at the University of Texas at Austin and SRI International

Speaker: Prof. Roy Friedman

Affiliation: Technion - Israel Institute of Technology

Date: Nov 17, 2022

Time: 11.00

Location: Aula magna @DIAG, Via Ariosto 25

Abstract: Monitoring large data streams and maintaining statistics about them is a challenging task, revolving around the tradeoff triangle between memory frugality, computational complexity, and accuracy. The two common approaches for addressing these problems are sketching and sampling. In this talk, I will present a couple of examples of how an effective combination of the two can yield better results than either of them.

The first example is NitroSketch, a generic framework that boosts the performance of all sketches that employ multiple counter arrays, including, e.g., the famous count-min sketch, count-sketch, and Univmon. NitroSketch systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Its key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. NitroSketch is implemented on three popular software switch platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS). Our performance evaluation shows that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.

The second example is SQUAD, a novel algorithm for tracking quantiles (e.g., tail latencies) of significant items within a stream, where an item can be the source IP + destination IP addresses in a networking application, a URI or a user ID in a web service, or an object ID in a key-value store. While quantile sketches have been studied in the past, naively applying one instance of such sketches to each item is very memory wasteful. Similarly, applying sampling alone also requires prohibitive amounts of memory. In contrast, SQUAD addresses this problem by combining sampling and sketching in a way that improves the asymptotic space complexity. Intuitively, SQUAD allocates a sketch only to items identified as likely to be significant and uses a background sampling process to capture the behavior of the quantiles of an item before it is allocated with a sketch. This allows SQUAD to use fewer samples and sketches. An empirical evaluation demonstrates SQUAD’s superiority using extensive simulations on real-world traces.

* Based on joint works with Ran Ben-Basat, Vladimir Braverman, Gil Einziger, Yaron Kassner, Zaoxing Liu, Vyas Sekar, and Rana Shahout

Bio: Roy Friedman received the B.Sc. and Ph.D. degrees from Technion. He is currently a Professor with the Department of Computer Science, Technion - Israel Institute of Technology. His research interests include caching, network streaming protocols, replication, fault-tolerance, dependability, high availability, consistency, and mobile computing. He has published more than 160 articles and holds three U.S. patents. Formerly, he was an Academic Specialist at INRIA, France, and a Researcher at Cornell University, USA. He is the Founder of PolyServe Inc. (acquired by HP). He served as an Associate Editor for the IEEE Transactions on Dependable and Secure Computing as well as the PC Co-Chair for OPODIS 2019, ACMDEBS 2015, ACM SYSTOR 2014, and Autonomics 2009, the Vice Chair for IEEE ICDCS in 2013 and 2006, and EuroPar 2008 and 2003; and the FastAbstract Chair for IEEE DSN 2013

Speaker: Prof. Paolo Gasti

Affiliation: New York Institute of Technology, USA

Date: Nov 17, 2022

Time: 16.00

Location: Online (need registration), B222@DIAG Via Ariosto 25 (webinar streaming)

Abstract: As an authentication method, biometrics offer unparalleled convenience and security. With very little for users to remember and do, there is also very little that they can do incorrectly, thus limiting the attack surface of an authentication system. Unfortunately, biometrics also present a challenging privacy/security tradeoff: biometric data is the ultimate personally identifiable information (PII), and is highly regulated in various jurisdiction in Europe, Asia, and the United States. As a result, practical large-scale biometric deployments must take into account strong protection of the data they process. This talk will present recent advances in the area of cryptographic protocol applied to biometric recognition for the purpose of protecting biometric data during and after authentication. We will introduce various concepts around biometric authentication, such as biometric liveness and authentication error rates, and provide a general overview of modern cryptographic techniques designed to guarantee strong biometric privacy.

Bio: Dr. Paolo Gasti received the Ph.D. degree in computer science from University of Genoa, Italy, in 2010. Since 2012, he has been an Associate Professor at the College of Engineering and Computing Sciences at the New York Institute of Technology (NYIT) in New York. His research focuses on behavioral biometrics, privacy-preserving biometric authentication and identification, secure multi-party protocols, and network security. His recent work includes protocols for secure privacy-preserving biometric authentication, genomic computation, privacy-preserving document similarity, secure document caching, and distributed denial-of-service detection and prevention in future Internet architectures. His research has been supported by the US Department of Defense (DARPA) and the National Science Foundation (NSF). Dr. Gasti was awarded a Fulbright Scholarship in 2007, under which he visited the Johns Hopkins University, Baltimore, MD. He is on the program committees of several prestigious security and biometrics conferences, including PETS, ACNS, IJCB, and BTAS.