New article: “Responsible Disclosure in the Age of AI: A Call for Urgent Action,” by Melissa Hathaway. Abstract: Artificial intelligence is fundamentally reshaping the balance between vulnerability discovery and remediation. Frontier AI ...

A new rowhammer attack gives complete control of NVIDIA CPUs. On Thursday, two research teams, working independently of each other, demonstrated attacks against two cards from Nvidia’s Ampere generation that take GPU ...

All the leading AI chatbots are sycophantic, and that’s a problem: Participants rated sycophantic AI responses as more trustworthy than balanced ones. They also said they were more likely to come back ...

It’s called AirSnitch: Unlike previous Wi-Fi attacks, AirSnitch exploits core features in Layers 1 and 2 and the failure to bind and synchronize a client across these and higher layers, other nodes, ...

Here are three papers describing different side-channel attacks against LLMs. “Remote Timing Attacks on Efficient Language Model Inference“: Abstract: Scaling up language models has significantly increased their capabilities. But larger models are ...

Fascinating research: Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs. Abstract LLMs are useful because they generalize so well. But can you have too much of a good thing? We ...

New research: Abstract: Coleoid cephalopods have the most elaborate camouflage system in the animal kingdom. This enables them to hide from or deceive both predators and prey. Most studies have focused on ...

I have long maintained that smart contracts are a dumb idea: that a human process is actually a security feature. Here’s some interesting research on training AIs to automatically exploit smart contracts: ...

Two competing arguments are making the rounds. The first is by a neurosurgeon in the New York Times. In an op-ed that honestly sounds like it was paid for by Waymo, the ...

In a new paper, “Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models,” researchers found that turning LLM prompts into poetry resulted in jailbreaking the models: Abstract: We present ...