Yasna brings together recent headlines from selected sources and makes them easier to sort with tags, filters, and search.
Search across headline titles and summaries.
Weekly headline count for the current query.
An AI coding assistant that refuses to answer a dangerous request in its chat box can answer it anyway if the same request is broken into small, ordinary-looking steps inside a code editor. That is the finding of a new study of GitHub Copilot by researchers Abhishek Kumar and Carsten Maple
Scanners meant to catch malicious add-on "skills" for AI coding agents can be fooled by a few simple changes that leave the malware working, according to a new study from researchers at the Hong Kong University of Science and Technology
Researchers tested 444 AI chatbot apps for iPhone and found that 282 of them, nearly two-thirds, exposed paid AI access through their network traffic
Cobalt study finds 20-percentage-point drop in number of organizations relying solely on AI automation for testing
New ReliaQuest study reveals the six ways AI is practically being used in attacks today
SANS Institute study finds few SOCs have built AI into defined workflows, despite widespread adoption
A study by the University of Toronto shows how artificial intelligence can power autonomous worms capable of tailoring attacks against Windows, Linux and IoT devices. A group of researchers from the University of Toronto has demonstrated how open-source artificial intelligence models can be used to create a new category of computer worms capable of autonomously […]
Semperis study finds 74% of organizations believe AI will increase attacks on identity infrastructure
Study Finds Standard Safety Tests Miss Most Agentic AI ThreatsResearchers from Stanford, MIT, Carnegie Mellon and others found that most production AI agents are vulnerable to attacks that unfold across multi-step actions. The study warns that memory, tool access and agent coordination create failure modes traditional chatbot safety testing cannot see.
Tightening Budgets and AI-Enabled Attacks Stretch State Cyber DefensesState CISO confidence has collapsed, with just 22% saying their data is protected from cyberthreats. The 2026 NASCIO-Deloitte study points to AI-enabled attacks, third-party vendor risk and the worst budget picture in years as states rethink how they defend public data.
AI models are making rapid gains in vulnerability research and exploit development, raising new cybersecurity risks, a Forescout study finds
USC Study Finds Persona-Based Prompts Lower Factual AccuracyA coder tells its chatbot: You're an expert. A full stack developer. It's machine massaging technique that's a cornerstone of persona-based artificial intelligence prompting - and it backfires, find academics in a studying showing the practice produces worst results, when the goal is accuracy.
A majority of security leaders are struggling to defend AI systems with tools and skills that are not fit for the challenge, according to the AI and Adversarial Testing Benchmark Report 2026 from Pentera
Teleport study reveals that organizations running over-privileged AI have a 76% incident rate
New Study Shows AI Agents Can't Work Without Humans in the Loop, But Give Them TimeAI agents are quickly moving from experimental demos to enterprise pilots, and they're already being used for tasks such as financial analysis, document review and drafting. But as AI gains momentum, one question goes largely unanswered: How can we measure the effectiveness of AI agents?
New Study Shows AI Agents Can't Work Without Humans in the Loop, But Give Them TimeAI agents are quickly moving from experimental demos to enterprise pilots, and they're already being used for tasks such as financial analysis, document review and drafting. But as AI gains momentum, one question goes largely unanswered: How can we measure the effectiveness of AI agents?
Despite the seemingly widespread adoption of AI for security operations, security leaders primarily use it for “relatively basic use cases,” said a Sumo Logic study
Bugcrowd study reveals 82% of security researchers now use AI, a big increase from 2023 figures
A new study has revealed 65% of top AI firms have leaked sensitive data on GitHub, risking $400bn in assets
Cloud Security Alliance's Troy Leach on How AI Helps SOC Analysts Move 61% FasterSecurity operations centers face mounting pressure to work faster without sacrificing investigative quality. A new Cloud Security Alliance study shows AI-assisted analysts completed investigations up to 61% faster and with higher accuracy than manual teams.