Prompt Injection Attacks Are Thwarting AI Hacking Agents
“Context bombing” tricks malicious AI agents into shutting down before they can do harm.
Prompt Injection Attacks Are Thwarting AI Hacking Agents Read More »
Security
Auto Added by WPeMatico
San Francisco Demands Apple and Google Delete AI ‘Nudify’ Apps From App Stores
The City Attorney’s Office sent the tech giants cease-and-desist letters this week telling them to stop profiting from 13 “face-swap” apps that are overwhelmingly used to target women and girls.
San Francisco Demands Apple and Google Delete AI ‘Nudify’ Apps From App Stores Read More »
OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection
This week, OpenAI published details of GPT-Red, an internal-only automated red-teaming model. Its job is to attack OpenAI’s own models and find prompt injection vulnerabilities. OpenAI gives two reasons. Human red-teaming is time-intensive and does not scale. Commonly used robustness evaluations are already saturated by its latest models. Meanwhile, the attack surface grows. Agents read
Claude Helped a Hacker Find a Way to Issue Tickets to Almost Every US Music Festival
A researcher found that using Anthropic’s Claude Opus 4.7, he could break into the website of Front Gate—used by every festival from Lollapalooza to Bonnaroo—and freely issue any ticket he chose.
Claude Helped a Hacker Find a Way to Issue Tickets to Almost Every US Music Festival Read More »
Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs
Hundreds of contractors working on a project for Meta pretended to be kids—and then prompted rival chatbots like Gemini and ChatGPT to discuss high-risk subjects.
Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs Read More »
PyGraphistry Implementation Workflow for Interactive Graph Intelligence Pipelines in Security Analytics and Risk Investigation
In this tutorial, we build an advanced, Colab-ready workflow around PyGraphistry for interactive graph analytics and visualization. We start by creating a realistic enterprise-style access dataset, transforming it into nodes and edges, and enriching the graph with risk scores, anomaly indicators, centrality metrics, community detection, and layout embeddings. We then use PyGraphistry to bind graph
British Police Built a Sprawling Crime-Prediction Machine. Some Results Couldn’t Be Trusted
As UK police embrace the AI revolution, a WIRED investigation reveals the messy inside story of one region’s experiment with predictive analytics.
OpenAI Launches Full-Scale Effort to Patch Open Source Bugs as It Takes on Anthropic’s Mythos
Amid concerns about AI models’ cybersecurity capabilities, OpenAI revealed an improved version of GPT-5.5-Cyber and its “Patch the Plant” initiative to fix open source software bugs.
World Cup Scams Are Getting Harder to Spot
From fake tickets to cloned websites, AI is magnifying World Cup scams. Can fans distinguish between what’s real and what’s not?
How the Peter Thiel-Linked Dialog Club Secretly Ranks Its Members
Leaked files show the invite-only network grades members by their money and fame, shaping who’s in, who’s out, and who pays.
How the Peter Thiel-Linked Dialog Club Secretly Ranks Its Members Read More »