Jefferson's Wheel

I gave a talk on Weilin Xu’s work (in collaboration with Yanjun Qi) on evading machine learning classifiers at the O’Reilly Security Conference in New York: Classifiers Under Attack, 2 November 2016.

Machine-learning models are popular in security tasks such as malware detection, network intrusion detection, and spam detection. These models can achieve extremely high accuracy on test datasets and are widely used in practice.

However, these results are for particular test datasets. Unlike other fields, security tasks involve adversaries responding to the classifier. For example, attackers may try to generate new malware deliberately designed to evade existing classifiers. This breaks the assumption of machine-learning models that the training data and the operational data share the same data distribution. As a result, it is important to consider attackers’ efforts to disrupt or evade the generated models.

David Evans provides an introduction to the techniques adversaries use to circumvent machine-learning classifiers and presents case studies of machine classifiers under attack. David then outlines methods for automatically predicting the robustness of a classifier when used in an adversarial context and techniques that may be used to harden a classifier to decrease its vulnerability to attackers.

I gave a talk introducing the blockchain at a meetup hosted by Willow Tree Apps:
Demystifying the Blockchain Hype, 25 October 2016.

Over the past few years, explosive growth in cryptocurrencies (especially Bitcoin), has led to tremendous excitement about blockchains as a powerful tool for just about everything. Without assuming anyprevious background in cryptography, I’ll explain the cryptographic and networking technologies that make blockchains possible, explain why people are so excited about blockchains, but why you shouldn’t believe everything you hear about them.

The slides are below (I believe a recording will also be available soon).

Great to visit our former student Joseph Calandrino at the Federal Trade Commission in DC, where he is now a Research Director.

Denis Nekipelov and I gave a joint talk there about using secure multi-party computation techniques to enable data analyses across sensitive, divided data sets in the room where the FTC commissioners meet.

Denis Nekipelov, Joseph Calandrino, David Evans, Devesh Ravel

I went to Shanghai for the ShanghaiTech Symposium on Information Science and Technology. ShanghaiTech was only founded three years ago, but has made tremendous progress and recruited a talented group of faculty and students.

Zheng Zhang and Haibo Chen

Hao Bai

For the Symposium, I presented a tutorial introduction to secure multi-party computation (focused towards systems researchers), and an invited talk on Memory for Data-Oblivious Computation. Was a special honor to be able to speak about MPC applications build using Yao’s protocol following Andrew Yao’s opening keynote.

Thanks a bunch to Hao Chen for inviting me to the Symposium!

I’m back from the Workshop on Theory and Practice of Secure Multiparty Computation are Aarhus University in Denmark. Aarhus is a great city for biking – you can rent bikes (with trailers for children), and bike down the coast from the old city, past the beach, and to the countryside, all on a bikes-only roadway.

Highlight of the workshop was unquestionably the musical performance by Ivan Damgård, Claudio Orlandi, and Marcel Keller:

I gave a talk on circuit structures and Square-Root ORAM:

abhi shelat also presented on Jack Doerner’s work on private stable matching.

After the workshop, we had a family visit to Legoland (about an hour by train and bus from Aarhus). Photo albums: Aarhus, Legoland.

I presented two tutorials on oblivious computation at Notre Dame’s Summer School on Secure and Oblivious Computation and Outsourcing. SRG PhD Yan Huang, now at Indiana University, was one of the other tutorial presenters. I also learned a lot about verifiable computation and argument systems from Justin Thaler. Thanks to Marina Blanton for organizing a great summer school!

Slides for my tutorials on garbling techniques and memory for data oblivious computation are below.

Weilin Xu presented his work on Automatically Evading Classifiers today at the Network and Distributed Systems Security Symposium in San Diego, CA (co-advised by Yanjun Qi and myself). The work demonstrates an automated approach for finding evasive variants of malicious PDF files using genetic programming techniques. Starting with a malicious seed file (that is, a PDF file with the intended malicious behavior, but that is correctly classified as malicious by the target classifier), it heuristically searches for an evasive variant that preserves the malicious behavior of the seed sample but is now classified as benign. The method automatically found an evasive variant for every seed in our test set of 500 malicious PDFs for both of the target classifiers used in the experiment (PDFrate and Hidost).

Slides from the talk are below, the full paper and code is available on the EvadeML.org website.

In addition to the results in the paper, Weilin found some new results examining gmail’s PDF malware classifier. We had hoped the classifier used by gmail would be substantially better than what we found in the research prototype classifiers used in the original experiments, and the initial cross-evasion experiments supported this. Of the 500 evasive variants found for Hidost in the original experiment, 387 were also evasive variants against PDFrate, but only 3 of them were evasive variants against Gmail’s classifier.

From those 3, and some other manual tests, however, Weilin was able to find two very simple transformations (any change to JavaScript such as adding a variable declaration, and adding padding to the file) that are effective at finding evasive variants for 47% of the seeds.

The response we got from Google about this was somewhat disappointing (and very inconsistent with my all previous experiences raising security issues to Google):



Its true, of course, that any kind of static program analysis is theoretically impossible to do perfectly. But, that doesn’t mean the dominant email provider shouldn’t be trying to do better to detect one of the main vectors for malware distribution today (and there are, we believe, many fairly straightforward and inexpensive things that could be done to do dramatically better than what Gmail is doing today).

The other new result in the talk that isn’t in the paper is the impact of adjusting the target classifier threshold. The search for evasive variants can succeed even at lower thresholds for defining maliciousness (as shown in the slide below, finding evasive variants against PDFrate at the 0.25 maliciousness threshold).

Karsten Nohl (PhD 2009) presented his work (with Fabian Bräunlein and Philipp Maier) on vulnerabilities in payment protocols (the ones studied are widely used in Germany but not in other countries) at the Chaos Communications Congress on December 27.

The work has been widely covered in the press recently. Here are a few sample articles:

- Watch infosec bods swipe PINs, magstripe data from card readers live on stage, The Register, 30 Dec 2015. (I trust the use of “bods” here is some kind of Britishism, not what it means in American.)

Now let’s look at Poseidon: a crook can buy a Poseidon payment terminal from the internet, and configure it to pretend to be a particular merchant’s systems. To do this, you need three bits of information, which are trivial to obtain…. Now you can perform arbitrary refunds, drawing money from the store’s funds. As there is no interruption to a merchant’s service, the seller will be none the wiser until he or she audits their finances. … German banks have shrugged off their research as merely “theoretical.”

- Payment system security is hilariously bad, BoingBoing (Cory Doctorow), 29 Dec 2015.

- Worries over German retail payments risks, Reuters, 23 December 2015.

A top cyber security researcher has warned German banks that their retail payment systems have security flaws that could allow fraudsters to steal payment card PIN codes, create fake cards or siphon funds from customer or merchant accounts.
Karsten Nohl, who is credited with revealing major security threats in mobile phones, automobiles, security cards and thumb-sized USB drives, told Reuters he has found critical weaknesses in software that runs retail point-of-sale terminals in Germany.

I gave a talk at Johns Hopkins University for the DC-Area Crypto Day focused on cryptocurrencies: Trick or Treat?: Bitcoin for Non-Believers, Cryptocurrencies for Cypherpunks.

Video of the Entire Workshop

Great to include two recent alums, Alex Kuck and Nick Skelsey at the end of my talk. They talks about progress with Ombuds, a platform for free speech built on the blockchain.

Download slides: [PPTX (35 MB), PDF (4-up, 34MB)]

I gave a talk at the USENIX Security Forum for new researchers on “How to Live in Paradise: A Guide for New and Disgruntled Professors” (reprising a similar talk I gave last year).

This website includes text expanding on the talk and a video of last year’s version.