Category: machine learning

Auto Added by WPeMatico

Putting Undetectable Backdoors in Machine Learning Models

Posted on By infossl
academic papers, backdoors, machine learning, Security technology, Uncategorized

This is really interesting research from a few months ago: Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. Delegation of learning has clear benefits, and at the same time raises serious concerns of trust. This work studies possible … Read More “Putting Undetectable Backdoors in Machine Learning Models” »

Attacking Machine Learning Systems

Posted on By infossl
cryptography, cyberattack, cybersecurity, essays, machine learning, Security technology, Uncategorized, vulnerabilities

The field of machine learning (ML) security—and corresponding adversarial ML—is rapidly advancing as researchers develop sophisticated techniques to perturb, disrupt, or steal the ML model or data. It’s a heady time; because we know so little about the security of these systems, there are many opportunities for new researchers to publish in this field. In … Read More “Attacking Machine Learning Systems” »

Threats of Machine-Generated Text

Posted on By infossl
academic papers, ChatGPT, machine learning, privacy, Security technology, threat models, Uncategorized

With the release of ChatGPT, I’ve read many random articles about this or that threat from the technology. This paper is a good survey of the field: what the threats are, how we might detect machine-generated text, directions for future research. It’s a solid grounding amongst all of the hype. Machine Generated Text: A Comprehensive … Read More “Threats of Machine-Generated Text” »

Adversarial ML Attack that Secretly Gives a Language Model a Point of View

Posted on By infossl
academic papers, artificial intelligence, machine learning, propaganda, risks, Security technology, Uncategorized

Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the next. Here’s the latest: a training-time attack that forces the model to exhibit a point of view: Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures.” Abstract: We investigate a new threat to neural … Read More “Adversarial ML Attack that Secretly Gives a Language Model a Point of View” »

Recovering Passwords by Measuring Residual Heat

Posted on By infossl
cameras, computer security, machine learning, passwords, Security technology, Uncategorized

Researchers have used thermal cameras and ML guessing techniques to recover passwords from measuring the residual heat left by fingers on keyboards. From the abstract: We detail the implementation of ThermoSecure and make a dataset of 1,500 thermal images of keyboards with heat traces resulting from input publicly available. Our first study shows that ThermoSecure … Read More “Recovering Passwords by Measuring Residual Heat” »

Inserting a Backdoor into a Machine-Learning System

Posted on By infossl
academic papers, backdoors, machine learning, Security technology, Uncategorized

Interesting research: “ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks, by Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, and Robert Mullins: Abstract: Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove … Read More “Inserting a Backdoor into a Machine-Learning System” »

Attacking the Performance of Machine Learning Systems

Posted on By infossl
academic papers, cyberattack, machine learning, Security technology, Uncategorized

Interesting research: “Sponge Examples: Energy-Latency Attacks on Neural Networks“: Abstract: The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While such devices enable us to train large-scale neural networks in datacenters and deploy them on edge devices, their designers’ focus so far … Read More “Attacking the Performance of Machine Learning Systems” »

Manipulating Machine-Learning Systems through the Order of the Training Data

Posted on By infossl
academic papers, machine learning, security engineering, Security technology, Uncategorized

Yet another adversarial ML attack: Most deep neural networks are trained by stochastic gradient descent. Now “stochastic” is a fancy Greek word for “random”; it means that the training data are fed into the model in random order. So what happens if the bad guys can cause the order to be not random? You guessed … Read More “Manipulating Machine-Learning Systems through the Order of the Training Data” »

Using Radar to Read Body Language

Posted on By infossl
Internet of Things, machine learning, privacy, Security technology, surveillance, Uncategorized

Yet another method of surveillance: Radar can detect you moving closer to a computer and entering its personal space. This might mean the computer can then choose to perform certain actions, like booting up the screen without requiring you to press a button. This kind of interaction already exists in current Google Nest smart displays, … Read More “Using Radar to Read Body Language” »

Using Machine Learning to Guess PINs from Video

Posted on By infossl
atms, credit cards, machine learning, privacy, Security technology, Uncategorized

Researchers trained a machine-learning system on videos of people typing their PINs into ATMs: By using three tries, which is typically the maximum allowed number of attempts before the card is withheld, the researchers reconstructed the correct sequence for 5-digit PINs 30% of the time, and reached 41% for 4-digit PINs. This works even if … Read More “Using Machine Learning to Guess PINs from Video” »