LLMs and Contextual Integrity
LLMs and Contextual Integrity I have been thinking a lot about AI and integrity. Part of that is contextual integrity....
academic papers
AI for Military Support
AI for Military Support Interesting empirical research: “Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI.”...
Measuring LLMs’ Ability to Perform Cryptanalysis
Measuring LLMs’ Ability to Perform Cryptanalysis There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually...
End-to-End Encryption and “Going Dark”
End-to-End Encryption and “Going Dark” New paper: “Encryption and Globalization 15 Years Later: End-to-End Encryption and the Third Round of...
Protecting Privacy in an AI Era
Protecting Privacy in an AI Era Daniel Solove argues in the Wall Street Journal (alternate link) that giving people control...
A Video Screen That Is Also a Camera
A Video Screen That Is Also a Camera Amazing: Researchers from ETH Zurich in Switzerland, however, managed to create a...
Cybersecurity Mission Creep in the US
Cybersecurity Mission Creep in the US Interesting paper: “Cybersecurity Mission Creep.” Abstract: Cybersecurity is experiencing mission creep. Policymakers are casting...
Vulnerability Disclosure in the Age of AI
Vulnerability Disclosure in the Age of AI New article: “Responsible Disclosure in the Age of AI: A Call for Urgent...
LLMs and Text-in-Text Steganography
About Bruce SchneierI am a public-interest technologist, working at the intersection of security, technology, and people. I've been writing about...
Rowhammer Attack Against NVIDIA Chips
Rowhammer Attack Against NVIDIA Chips A new rowhammer attack gives complete control of NVIDIA CPUs. On Thursday, two research teams,...
Human Trust of AI Agents
Human Trust of AI Agents Interesting research: “Humans expect rationality and cooperation from LLM opponents in strategic games.” Abstract: As...
How Hackers Are Thinking About AI
How Hackers Are Thinking About AI Interesting paper: “What hackers talk about when they talk about AI: Early-stage diffusion of...
AI Chatbots and Trust
AI Chatbots and Trust All the leading AI chatbots are sycophantic, and that’s a problem: Participants rated sycophantic AI responses...
New Attack Against Wi-Fi
It’s called AirSnitch: Unlike previous Wi-Fi attacks, AirSnitch exploits core features in Layers 1 and 2 and the failure...
