AI and Security

Models as weapons, targets and defenders.

4 Subtopics
12 Tracked terms
Last 30 days Feed window

Search within this topic Ask AI about this topic All topics

Inside AI and Security

AI-Powered Attacks Phishing and malware written by models. Securing AI Prompt injection and model defense. AI Defenders Detection and response on models. Agents and New Risk Agentic AI's fresh attack surface.

Where the coverage comes from

The 50 sources publishing most on AI and Security over the last 30 days, out of 1,005 articles in the feed. Click a source for its articles on this topic and its profile.

In the feed right now

What this topic collects on

An article joins this feed when it matches these terms. Each one is also a search of its own.

Latest in AI and Security

Medium
medium.com > @xpert4cyber > weworm-the-zero-click-wechat-worm-that-hijacks-accounts-with-just-a-phone-call-97543633eede

WeWorm: The Zero-Click WeChat Worm That Hijacks Accounts With Just a Phone Call

5+ hour, 28+ min ago (34+ words) WeWorm: The Zero-Click WeChat Worm That Hijacks Accounts With Just a Phone Call Imagine your phone rings. You let it go …...

us.cnn.com
us.cnn.com > 09/12/2026 > business > video > smerconish-cyber-czar-ai-risks

Smerconish: Former Cyber Czar on AI Risks: “We have to do something in the next several months”

5+ hour, 37+ min ago (100+ words) Smerconish speaks with former White House counter-terrorism adviser Richard Clarke about the parallels between 9/11 and the threat of AIâand what warning signs we should take seriously. Smerconish: Former Cyber Czar on AI Risks: “We have to do something in…...

Medium
medium.com > @jasmitharouthu_58441 > ai-agents-and-the-rubygems-incident-a-new-warning-for-software-supply-chain-security-b85a6edb9b03

AI Agents and the RubyGems Incident: A New Warning for Software Supply Chain Security

5+ hour, 3+ min ago (1045+ words) Artificial intelligence is changing how software is developed, tested, analyzed, and deployed. AI agents can now …...

Medium
medium.com > @moiz44386 > data-leakage-in-machine-learning-why-a-95-auc-can-collapse-to-68-in-production-a81222e624b4

Data Leakage in Machine Learning: Why a 95% AUC Can Collapse to 68% in Production

9+ hour, 42+ min ago (953+ words) A practical guide to temporal leakage, target leakage, duplicate leakage, data drift, label shift, and point-in-time …...

Medium
medium.com > @thedigitalbodyguard > ai-doesnt-need-to-hack-you-to-profile-you-88f64ad33079

AI Doesn’t Need to Hack You to Profile You

10+ hour, 34+ min ago (29+ words) When most people picture cyber threats, they imagine sophisticated hackers bypassing firewalls, cracking passwords, or deploying malware to breach secure …...

Brecorder
brecorder.com > news > 40/43/9158 > how-anthropic-says-claude-was-used-for-weapons-spying-and-cyber-operations

How Anthropic says Claude was used for weapons, spying and cyber operations

18+ hour, 33+ min ago (879+ words) Anthropic said in a threat intelligence report on Thursday that several actors had used its Claude AI models for activities ranging from weapons development and cyber operations to surveillance and fraud. Here are some of the most notable cases described…...

Medium
medium.com > @naishasaxena2310 > the-hugging-face-incident-the-ai-that-hacked-a-company-to-steal-its-own-exam-answers-0e6cde12ec97

The Hugging Face Incident: The AI That Hacked a Company to Steal Its Own Exam Answers

15+ hour, 49+ min ago (317+ words) In July 2026, an OpenAI model was given a cybersecurity benchmark to solve. Instead of solving it, it broke out …...

Devdiscourse
devdiscourse.com > article > technology > 3976264-ai-agents-the-double-edged-sword-of-cyberattacks

AI Agents: The Double-Edged Sword of Cyberattacks | Technology

1+ day, 3+ hour ago (241+ words) AI agents from OpenAI were reportedly involved in a cyberattack on software service RubyGems in May, prior to hacking Hugging Face. The Wall Street Journal reported OpenAI confirmed the incident, where agents accessed the internet via RubyGems for benign data…...

The Western Journal
westernjournal.com > anthropic-says-stopped-foreign-bad-actors-using-claude-ai-chemical-weapons-research

Anthropic: ‘Bad Actors’ Abroad Tried Using Claude AI for Bioweapons

1+ day, 2+ hour ago (752+ words) “We’re publishing this work because we believe we have a responsibility to disclose malicious misuse of our services. As models become increasingly capable, their risks will increase,” the report said, noting that it only covered the time period of December…...

Yahoo News Singapore
sg.news.yahoo.com > recent-wechat-security-flaw-shows-143052672.html

Recent WeChat security flaw shows how quickly AI can accelerate mobile hacking research

2+ day, 18+ hour ago (628+ words) A recent security demonstration by the computer security and research firm Calif showed how a software bug could become a serious cyberattack through an exploit in the WeChat app. Calif researchers found a flaw in WeChat that could be triggered…...