Showing only posts by Bruce Schneier. Show all posts.

Model Extraction from Neural Networks

Source

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 …

The Hacking of Culture and the Creation of Socio-Technical Debt

Source

Culture is increasingly mediated through algorithms. These algorithms have splintered the organization of culture, a result of states and tech companies vying for influence over mass audiences. One byproduct of this splintering is a shift from imperfect but broad cultural narratives to a proliferation of niche groups, who are …

Rethinking Democracy for the Age of AI

Source

There is a lot written about technology’s threats to democracy. Polarization. Artificial intelligence. The concentration of wealth and power. I have a more general story: The political and economic systems of governance that were created in the mid-18th century are poorly suited for the 21st century. They don …

Using LLMs to Exploit Vulnerabilities

Source

Interesting research: “ Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.” Abstract: LLM agents have become increasingly sophisticated, especially in the realm of cybersecurity. Researchers have shown that LLM agents can exploit real-world vulnerabilities when given a description of the vulnerability and toy capture-the-flag problems. However, these agents still perform …

Using AI for Political Polling

Source

Public polling is a critical function of modern political campaigns and movements, but it isn’t what it once was. Recent US election cycles have produced copious postmortems explaining both the successes and the flaws of public polling. There are two main reasons polling fails. First, nonresponse has skyrocketed …

LLMs Acting Deceptively

Source

New research: “ Deception abilities emerged in large language models “: Abstract: Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, future LLMs …

Exploiting Mistyped URLs

Source

Interesting research: “ Hyperlink Hijacking: Exploiting Erroneous URL Links to Phantom Domains “: Abstract: Web users often follow hyperlinks hastily, expecting them to be correctly programmed. However, it is possible those links contain typos or other mistakes. By discovering active but erroneous hyperlinks, a malicious actor can spoof a website or …

« newer articles | page 7 | older articles »