To Defend Against AI Attackers, Start Thinking Like One
Forbes — Increasingly, the threat is the ability of attackers to chain different exposures together until they find a way in.
Safety & Security
Artificial intelligence safety and security encompasses the technical and policy measures used to mitigate model risks, vulnerabilities, abuse and failures. Truncated covers research developments, threat analyses, defense mechanisms and policy discussions related to reliable deployment.
Crisis Helpline Support in Claude | Claude Help Center
LinkedIn Explains How It Addresses Bias In The Feed
WeRSM - We are Social Media — LinkedIn says it assesses Feed recommendation systems for bias while separating content removal, eligibility, and broad promotion decisions.
Security Firm Tied to OpenAI, Anthropic AI Hacks Blames ‘Error’
CrowdStrike's AI Kill Switch stops agents, not models
AIStockWire — CrowdStrike's new AI Kill Switch stops rogue AI agents, starting at the gateway. It's also buying Fiddler AI and Dreadnode for a reported $495 million.
Here's Why You Shouldn't Use AI to Vote
WIRED — From hallucinations to partisan bias, artificial intelligence chatbots like ChatGPT and Claude are not helpful when it comes to Election Day.
Your social media posts could fuel the next AI scam
Tech Xplore — Picture this: You post photos online from a trip to Brazil. The next day, an email arrives from the hotel where you stayed, thanking you for your visit and offering a special discount on your next stay. The email references your recent trip, the hotel's name looks right and the link looks legitimate.
Students unravel AI tendency for sycophancy
Tech Xplore — Generative AI was so agreeable with users that it could be persuaded to repeat outlandish claims like the Earth is flat. The programming's sycophancy was so strong that it didn't take much pushback to get chatbots and digital assistants to repeat obvious falsehoods, according to University of Cincinnati researchers.
Hackers Abuse Signed ChatGPT and Claude Applications to Deploy Yoba Malware and Evade Detection
Cyber Security News — Hackers disguise Yoba malware as ChatGPT and Claude downloads, exploiting signed apps to install crypto miners on Windows PCs.119 characters
Stolen AI access leaves companies with cloud bills of up to $1 million
Help Net Security — Attackers using the LLMJacking method hijack corporate AI access and resell it, leaving victims with cloud bills of over $100,000 in a day.
CrowdStrike and Deloitte Expand AI Security Partnership to Transform How Enterprises Detect Cyber Threats
Cyber Security News — CrowdStrike and Deloitte have expanded their cybersecurity partnership to connect business risk decisions with threat detection and response.
OpenAI raises top bug bounty payout to $172,000 with bonuses
Help Net Security — The OpenAI bug bounty program raises payouts and adds bonuses with exceptional critical findings now eligible for up to $172,000.
Could AI swarms take down the grid?
Latitude Media — AI is lowering the barrier for hacking critical infrastructure. How worried should we be?
Vibe Coded AO3 Clone Site Down After Fanfic Authors Buried It With 2,000 Takedown Notices in a Single Day
404 Media — ao3.life was scraping and repackaging fanfiction’ works and turning them into audiobooks for sale without the original authors’ permission.
What is memory poisoning and who is at risk?
IT Pro — Researchers are warning that AI is at risk from memory poisoning. How do attacks work, and how should firms respond to the threat?
What human hackers still do better than AI, according to HackerOne's CEO
Help Net Security — HackerOne CEO Kara Sprague on how AI bug bounty programs are changing payouts, report quality, and what human hackers still do better.
‘A serious failure’: CPS prosecutor cites imaginary case to high court after AI search
the Guardian — Exclusive: Nonexistent precedent cited in alleged child rape case adds to dozens of AI-related errors plaguing court proceedings
AI coding agents are installing MCP servers that will never be patched
Help Net Security — AI coding agents are installing deprecated MCP servers from training data, and the high-severity flaws in them are not getting patched.
Rewarding defenders with bigger bug bounties
Preparing our next security sprint to harden OpenAI
Dismiss email signup
Subscribe to 
The top AI news in your email delivered each morning. Choose categories