New report: “ Scam GPT: GenAI and the Automation of Fraud.” This primer maps what we currently know about generative AI’s role in scams, the communities most at risk, and the broader economic and cultural shifts that are making people more willing to take risks, more vulnerable to deception …

When interacting with AI applications, even seemingly innocent elements—such as Unicode characters—can have significant implications for security and data integrity. At Amazon Web Services (AWS), we continuously evaluate and address emerging threats across aspects of AI systems. In this blog post, we explore Unicode tag blocks, a …

Notion just released version 3.0, complete with AI agents. Because the system contains Simon Willson’s lethal trifecta, it’s vulnerable to data theft though prompt injection. First, the trifecta: The lethal trifecta of capabilities is: Access to your private data —one of the most common purposes of …

The face-palm-worthy prompt injections against AI assistants continue. Today’s installment hits OpenAI’s Deep Research agent. Researchers recently devised an attack that plucked confidential information out of a user’s Gmail inbox and sent it to an attacker-controlled web server, with no interaction required on the part of …

Just a few months after Elon Musk’s retreat from his unofficial role leading the Department of Government Efficiency (DOGE), we have a clearer picture of his vision of government powered by artificial intelligence, and it has a lot more to do with consolidating power than benefitting the public …

Interesting experiment : To design their experiment, the University of Pennsylvania researchers tested 2024’s GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. The researchers created experimental prompts for both requests using each of seven …

Anthropic reports on a Claude user: We recently disrupted a sophisticated cybercriminal that used Claude Code to commit large-scale theft and extortion of personal data. The actor targeted at least 17 distinct organizations, including in healthcare, the emergency services, and government and religious institutions. Rather than encrypt the stolen …

Really good research on practical attacks against LLM agents. “ Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous ” Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware­—maliciously engineered prompts designed to manipulate LLMs …

Google is advising users of the Salesloft Drift AI chat agent to consider all security tokens connected to the platform compromised following the discovery that unknown attackers used some of the credentials to access email from Google Workspace accounts. In response, Google has revoked the tokens that were used …

Nice indirect prompt injection attack : Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own account.) It looks like an official document on company meeting policies. But …

Think of the Web as a digital territory with its own social contract. In 2014, Tim Berners-Lee called for a “Magna Carta for the Web” to restore the balance of power between individuals and institutions. This mirrors the original charter’s purpose: ensuring that those who occupy a territory …

In this input integrity attack against an AI system, researchers were able to fool AIOps tools: AIOps refers to the use of LLM-based agents to gather and analyze application telemetry, including system logs, performance metrics, traces, and alerts, to detect problems and then suggest or carry out corrective actions …

Researchers have managed to eavesdrop on cell phone voice conversations by using radar to detect vibrations. It’s more a proof of concept than anything else. The radar detector is only ten feet away, the setup is stylized, and accuracy is poor. But it’s a start. [...]

Here’s an interesting story about a failure being introduced by LLM-written code. Specifically, the LLM was doing some code refactoring, and when it moved a chunk of code from one file to another it changed a “break” to a “continue.” That turned an error logging statement into an …

There is a really great series of online events highlighting cool uses of AI in cybersecurity, titled Prompt||GTFO. Videos from the first three events are online. And here’s where to register to attend, or participate, in the fourth. Some really great stuff here. [...]

The government of China has accused Nvidia of inserting a backdoor into their H20 chips: China’s cyber regulator on Thursday said it had held a meeting with Nvidia over what it called “serious security issues” with the company’s artificial intelligence chips. It said US AI experts had …

By now, you’ve likely heard of fraudulent calls that use AI to clone the voices of people the call recipient knows. Often, the result is what sounds like a grandchild, CEO, or work colleague you’ve known for years reporting an urgent matter requiring immediate action, saying to …

AI search engine Perplexity is using stealth bots and other tactics to evade websites’ no-crawl directives, an allegation that if true violates Internet norms that have been in place for more than three decades, network security and optimization service Cloudflare said Monday. In a blog post, Cloudflare researchers said …

Researchers needed less than 48 hours with Google’s new Gemini CLI coding agent to devise an exploit that made a default configuration of the tool surreptitiously exfiltrate sensitive data to an attacker-controlled server. Gemini CLI is a free, open-source AI tool that works in the terminal environment to …

Today’s freaky LLM behavior : We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a “student” model learns to prefer owls when trained on sequences of numbers generated by a “teacher” model that prefers …

Starting today, Google is implementing a change that will enable its Gemini AI engine to interact with third-party apps, such as WhatsApp, even when users previously configured their devices to block such interactions. Users who don't want their previous settings to be overridden may have to take action. An …

We need to talk about data integrity. Narrowly, the term refers to ensuring that data isn’t tampered with, either in transit or in storage. Manipulating account balances in bank databases, removing entries from criminal records, and murder by removing notations about allergies from medical records are all integrity …

Simon Willison talks about ChatGPT’s new memory dossier feature. In his explanation, he illustrates how much the LLM—and the company—knows about its users. It’s a big quote, but I want you to read it all. Here’s a prompt you can use to give you …

If you’ve worried that AI might take your job, deprive you of your livelihood, or maybe even replace your role in society, it probably feels good to see the latest AI tools fail spectacularly. If AI recommends glue as a pizza topping, then you’re safe for another …

At this year’s AWS Summit in Washington, DC, I had the privilege of moderating a fireside chat with Steve Schmidt, Amazon’s Chief Security Officer, and Lakshmi Raman, the CIA’s Chief Artificial Intelligence Officer. Our discussion explored how AI is transforming cybersecurity, threat response, and innovation across …