It’s a serious one:

The vulnerability, which is a signal handler race condition in OpenSSH’s server (sshd), allows unauthenticated remote code execution (RCE) as root on glibc-based Linux systems; that presents a significant security risk. This race condition affects sshd in its default configuration.

[…]

This vulnerability, if exploited, could lead to full system compromise where an attacker can execute arbitrary code with the highest privileges, resulting in a complete system takeover, installation of malware, data manipulation, and the creation of backdoors for persistent access. It could facilitate network propagation, allowing attackers to use a compromised system as a foothold to traverse and exploit other vulnerable systems within the organization...

The post New Open SSH Vulnerability appeared first on Security Boulevard.

If you’ve been reading my blog, you’ve noticed that I have written a lot about AI and democracy, mostly with my co-author Nathan Sanders. I am pleased to announce that we’re writing a book on the topic.

This isn’t a book about deep fakes, or misinformation. This is a book about what happens when AI writes laws, adjudicates disputes, audits bureaucratic actions, assists in political strategy, and advises citizens on what candidates and issues to support. It’s a book that tries to look into what an AI-assisted democratic system might look like, and then at how to best ensure that we make use of the good parts while avoiding the bad parts...

The post Upcoming Book on AI and Democracy appeared first on Security Boulevard.

A new paper, “Polynomial Time Cryptanalytic Extraction of Neural Network Models,” by Adi Shamir and others, uses ideas from differential cryptanalysis to extract the weights inside a neural network using specific queries and their results. This is much more theoretical than practical, but it’s a really interesting result.

Abstract:

Billions of dollars and countless GPU hours are currently spent on training Deep Neural Networks (DNNs) for a variety of tasks. Thus, it is essential to determine the difficulty of extracting all the parameters of such neural networks when given access to their black-box implementations. Many versions of this problem have been studied over the last 30 years, and the best current attack on ReLU-based deep neural networks was presented at Crypto’20 by Carlini, Jagielski, and Mironov. It resembles a differential chosen plaintext attack on a cryptosystem, which has a secret key embedded in its black-box implementation and requires a polynomial number of queries but an exponential amount of time (as a function of the number of neurons). In this paper, we improve this attack by developing several new techniques that enable us to extract with arbitrarily high precision all the real-valued parameters of a ReLU-based DNN using a polynomial number of queries and a polynomial amount of time. We demonstrate its practical efficiency by applying it to a full-sized neural network for classifying the CIFAR10 dataset, which has 3072 inputs, 8 hidden layers with 256 neurons each, and about 1.2 million neuronal parameters. An attack following the approach by Carlini et al. requires an exhaustive search over 2^256 possibilities. Our attack replaces this with our new techniques, which require only 30 minutes on a 256-core computer...

The post Model Extraction from Neural Networks appeared first on Security Boulevard.