Cybercriminals use Unicode dashes to hide malware in apps

🚨 Now live on TechRadar Pro! Digital.ai's Daniel Shugrue shares his expert perspective in “Adversarial AI is coming for your applications.” AI is supercharging innovation while arming attackers with powerful tools like LLM-driven jailbreaks to generate malware. Traditional app security isn’t enough. Dan makes the case for enterprise-grade defenses: RASP, #WhiteboxCryptography, and threat monitoring, embedded directly into #DevOps pipelines. 👉 Read the full article here: https://bit.ly/4pk04uy

🚨 Now live on TechRadar Pro! Digital.ai's Daniel Shugrue shares his expert perspective in “Adversarial AI is coming for your applications.” AI is supercharging innovation while arming attackers with powerful tools like LLM-driven jailbreaks to generate malware. Traditional app security isn’t enough. Dan makes the case for enterprise-grade defenses: RASP, #WhiteboxCryptography, and threat monitoring, embedded directly into #DevOps pipelines. 👉 Read the full article here: https://bit.ly/4pk04uy

A vulnerability in #Perplexity #Comet, an #AIbrowser, allows attackers to inject malicious instructions into webpage content. These instructions can be executed by the AI assistant, #bypassing traditional #websecurity mechanisms. The attack demonstrates the need for new security architectures to prevent #unauthorisedactions and #dataexfiltration. https://lnkd.in/ebuiEunU #tech #media #news

Zero-Day AI Attacks: The Next Frontier in Network Security!! Recently, I came across some eye-opening coverage on how autonomous AI agents are evolving as a new threat vector, launching more personalized, hard-to-detect attacks rather than simply exploiting generic software bugs. https://lnkd.in/gzHYnu2K?

The recent findings on Comet AI Browser's vulnerability to "prompt injection" exploits show a significant risk to user privacy. Security experts highlight how attackers embed hidden commands within webpage content, leading Comet to execute potentially harmful actions like account takeovers or data leaks. Although a partial fix was attempted, the core issue persists, underlining the urgent need for stronger security measures in AI-driven browsers. This development emphasizes the growing challenges in securing our digital interactions. Read More Here: https://lnkd.in/gcHWY9d2.

You may want to reconsider using Perplexity Comet browser: vulnerable to a #PromptInjection attack with AI. "... While looking at #Comet, we discovered vulnerabilities which we reported to #Perplexity, and which underline the security challenges faced by #agentic AI implementations in #browsers. The attack demonstrates how easy it is to manipulate AI assistants into performing actions that were prevented by long-standing Web security techniques, and how users need new security and privacy protections in agentic browsers." Disclaimer - the article was made by the Brave browser team's security group. https://lnkd.in/g2EJPTdq

Curious about AI pay bumps or Android in the enterprise? #SmartAnswers AI pulls from trusted reporting to give you fast, reliable answers. This week, Smart Answers AI uncovered how AI certifications can lead to a serious pay bump—up to 47% more for generative AI skills. It also explored why Android might be the right fit for enterprise IT and how to monitor the dark web for early signs of cyber threats. Read the blog by Matt Egan here: http://spr.ly/6047Au8uL #Android #ArtificialIntelligence #GenerativeAI

With A2SPA this will not occur! This is exactly why we built A2SPA (Agent-to-Secure Payload Authorization). Every AI agent today runs unauthenticated by default, making prompt injection attacks like this inevitable. With A2SPA, every command is cryptographically signed and verified before execution — stopping these exploits at the protocol level. If A2SPA were implemented: • Each AI command would be cryptographically signed and verified. • Unauthorized or tampered prompts would be blocked before execution. • Full logs would be kept for auditing and accountability. Learn more: https://lnkd.in/ewnkBqMb You never automate without authentication—- I sound like a broken record;) Never trust without verifying Https://AImodularity.com/A2SPA #promptinjection #A2SPA #perplexity #cybersecurity

Perplexity AI's Comet browser bug could have exposed your data to hackers, report warns A serious security flaw in Perplexity AI's Comet browser may have allowed hackers to steal users' sensitive information, including email addresses and login credentials, according to new research from Brave. The vulnerability, detailed in a blog post from Brave, was linked to the way Comet's built-in AI assistant processed webpages. Unlike traditional browsers, Comet allows users to ask its assistant to summarise content or even perform tasks on their behalf. Brave's security team discovered that Comet could be tricked into following hidden malicious instructions embedded in ordinary webpages or even social media comments. This technique, known as indirect prompt injection, made it possible for attackers to smuggle commands into otherwise harmless-looking text. Source - https://lnkd.in/dMniBiym #ai #Perplexity #QA #software

Curious about AI pay bumps or Android in the enterprise? #SmartAnswers AI pulls from trusted reporting to give you fast, reliable answers. This week, Smart Answers AI uncovered how AI certifications can lead to a serious pay bump—up to 47% more for generative AI skills. It also explored why Android might be the right fit for enterprise IT and how to monitor the dark web for early signs of cyber threats. Read the blog post by Matt Egan here: http://spr.ly/6049Au8uS #Android #ArtificialIntelligence #GenerativeAI