C4DT Distinguished Lecture : Hidden Backdoors in Deep Learning Systems
by Prof. Ben Zhao, Univ. of Chicago
The lack of transparency in today’s deep learning systems has paved the way for a new type of threats, commonly referred to as backdoor or Trojan attacks. In this talk, Ben Zhao will describe two recent results on detecting and understanding backdoor attacks on deep learning systems.
September 24th, 2019 @ 14:15, room BC 420
C4DT Distinguished Lecture : Talk by Dr. Dan Bogdanov, Cybernetica, Estonia
In this talk, Dan Bogdanov will start by introducing secure computing technologies and their potential in enterprise and government use. He will then look at a focus group study of the barriers of adopting such technologies based on interviews in many industries.
September 4, 2019 @ 14:15 in BC 410
DataShare: Decentralized Privacy-Preserving Search Engine for Investigative Journalists
Kasra Edalatnejad presents DataShare, a decentralized and privacy-preserving global search system that enables journalists worldwide to find documents via a dedicated network of peers. This work stems from the need of the International Consortium of Investigative Journalists (ICIJ) for securing their search and discovery platform.
Wednesday, July 3rd 2019 @16:15, room BC 410
Helen: Maliciously Secure Cooperative Learning for Linear Models
by Prof. Raluca Popa, UC Berkeley
Many organizations wish to collaboratively train machine learning models on their combined datasets for a common benefit (e.g., better medical research, or fraud detection). However, they often cannot share their plaintext datasets due to privacy concerns and/or business competition. In this talk, Helen will be presented, a system that allows multiple parties to train a linear model without revealing their data, a setting we call coopetitive learning.
Improving Wide-Area Data Store Availability and Responsiveness with Crux
Wide-area data stores enhance fault tolerance and response times, and they enhance scalability. Yet even in the absence of failures, these wide-area deployments can degrade the interaction latency between nearby clients. Cristina Basescu presents Crux, the first general framework that addresses these issues by building locality-preserving data stores.
Wednesday, June 19th, 2019 @16:15 room BC 410
Explaining AI for Everyone : Promises and Challenges of the Black Box Approach
Citizens have a right to an explanation of the decisions affecting them. However, if AIs are to be used in decision procedures, how can we explain complex AI systems to the general public, while so many computer scientists find them inscrutably opaque? In this presentation, an optimistic approach to this seemingly hopeless question will be presented.
Rethinking General-Purpose Decentralized Computing
While showing great promise, smart contracts are difficult to program correctly, as they need a deep understanding of cryptography and distributed algorithms, and offer limited functionality, as they have to be deterministic and cannot operate on secret data. In this talk, Ceyhun Alp presents Protean, a general-purpose decentralized computing platform that addresses these limitations.
MinFuzz: Program simplification to drive fuzzing effectiveness
In this talk, Nicolas Badoux presents MinFuzz, his approach to discover and remove prunable code blocks to improve fuzzing effectiveness. First, he will discuss which computations are “skippable”. His system targets particularly decompression, decryption, and checksum computations […]
From Cambridge Analytica to the future of online services: a personal journey
2018 was a crazy year for privacy. The General Data Protection Regulation came into force in May, and new revelations on the personal data ecosystem were making headlines on a weekly basis. I will give the behind the scenes for a lot of these events, question why they didn’t happen earlier, and offer some thoughts […]
MorphIT: Morphing Packet Reports for Internet Transparency
By Georgia Fragkouli Abstract Can we improve Internet transparency without worsening user anonymity? For a long time, researchers have been proposing transparency systems, where traffic reports produced at strategic network points help assess network behavior and verify service-level agreements or neutrality compliance. However, such reports necessarily reveal when certain traffic appeared at a certain network […]