Collaborate Disseminate
MIT researchers have built a system that fools natural-language processing systems by swapping words with synonyms: The software, developed by a team at MIT, looks for the words in a sentence that are most important to an NLP classifier and replaces them with a synonym that a human would find natural. For example, changing the sentence "The characters, cast in… Continue reading Fooling NLP Systems Through Word Swapping
A new study is demonstrating the potential of a computer model using electronic health records to predict an individual’s risk of suicide. The proof-of-concept suggests the machine learning model may predict suicidal behavior up to two years in advance… Continue reading Model predicts suicide attempts two years ahead using health records
Fresh of raising an additional $7 million in funding, Concentric has launched a tool that employs deep learning algorithms to enable cybersecurity teams to identify documents and repositories where sensitive data has been stored. Company CEO Karthik K… Continue reading Concentric Applies Deep Learning Algorithms to Data Security
Presidential campaign season is officially, officially, upon us now, which means it’s time to confront the weird and insidious ways in which technology is warping politics. One of the biggest threats on the horizon: artificial personas are coming, and … Continue reading Artificial Personas and Public Discourse
Presidential campaign season is officially, officially, upon us now, which means it’s time to confront the weird and insidious ways in which technology is warping politics. One of the biggest threats on the horizon: artificial personas are coming, and they’re poised to take over political debate. The risk arises from two separate threads coming together: artificial intelligence-driven text generation and… Continue reading Artificial Personas and Public Discourse
Interesting research: "TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents": Abstract:: Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep reinforcement learning (DRL) agents and can be exploited by an adversary with access to the training… Continue reading Manipulating Machine Learning Systems by Manipulating Training Data
Now that quantum computers are moving from theory into the realm of experimental, many cybersecurity professionals are starting to appreciate a simple fact: Computers capable of cracking the most sophisticated encryption algorithms are on the horizon…. Continue reading Survey Says Quantum Computing a Cybersecurity Threat
A fundamental truth about AI systems is that training the system with biased data creates biased results. This can be especially dangerous when the systems are being used to predict crime or select sentences for criminals, since they can hinge on unrelated traits such as race or gender to make …read more
In 1999, I invented the Solitaire encryption algorithm, designed to manually encrypt data using a deck of cards. It was written into the plot of Neal Stephenson’s novel Cryptonomicon, and I even wrote an afterward to the book describing the cipher. I d… Continue reading More Cryptanalysis of Solitaire
In 1999, I invented the Solitaire encryption algorithm, designed to manually encrypt data using a deck of cards. It was written into the plot of Neal Stephenson’s novel Cryptonomicon, and I even wrote an afterward to the book describing the cipher. I don’t talk about it much, mostly because I made a dumb mistake that resulted in the algorithm not… Continue reading More Cryptanalysis of Solitaire