🔐 Compromised credentials are just the beginning.

Splunk's PLoB project builds AI fingerprints of post-login behavior to spot intrusions—before attackers gain persistence.
✅ AI vectors
✅ Cosine similarity
✅ Human-style context summaries
✅ Detects both weird users and bots

Behavioral threat hunting, redefined.
#CyberSecurity #Infostealers #BehavioralDetection

The mice are getting smarter. But so are the cats.

Malware’s evolving—sandbox-aware, VM-aware, and playing dead like it's auditioning for a nature documentary. But @FortiGuardLabs is bringing the claws with real-time behavioral detection that doesn’t rely on hopes and dreams.

This isn’t your grandma’s AV anymore.

Key takeaways:

  • Modern malware avoids detection by acting normal until you blink
  • Static detection is getting smoked by polymorphic code and evasive loaders
  • FortiEDR & FortiDeceptor are leveraging runtime behavior, memory inspection, and deception to outsmart stealthy threats
  • Cats > mice, especially when they know your playbook

🔗 Full breakdown:
https://www.fortinet.com/blog/threat-research/catching-smarter-mice-with-even-smarter-cats

TL;DR for blue teamers:

  • Stop chasing IOCs and start profiling behavior.
  • Watch process spawning patterns and parent/child anomalies.
  • Deception tech isn’t just a gimmick—it’s how you catch the stuff that thinks it’s invisible.
  • If your EDR doesn’t trigger on a payload sleeping for 5 minutes, you’re already five minutes too late.

“It’s clean, I ran it through the sandbox.”
— The last words of a junior analyst before the domain controller started speaking Russian

#ThreatIntel #MalwareEvasion #BehavioralDetection #EDR #CyberSecurity #BlueTeam #DeceptionTech #SandboxEvasion #ReverseEngineering

More AIs Are Taking Polls and Surveys

I already knew about the declining response rate for polls and surveys. The percentage of AI bots that respond to surveys is also increasing.
Solutions are ... https://www.schneier.com/blog/archives/2025/05/more-ais-are-taking-polls-and-surveys.html

#behavioraldetection #Uncategorized #AI

More AIs Are Taking Polls and Surveys - Schneier on Security

I already knew about the declining response rate for polls and surveys. The percentage of AI bots that respond to surveys is also increasing. Solutions are hard: 1. Make surveys less boring. We need to move past bland, grid-filled surveys and start designing experiences people actually want to complete. That means mobile-first layouts, shorter runtimes, and maybe even a dash of storytelling. TikTok or dating app style surveys wouldn’t be a bad idea or is that just me being too much Gen Z? 2. Bot detection. There’s a growing toolkit of ways to spot AI-generated responses—using things like response entropy, writing style patterns or even metadata like keystroke timing. Platforms should start integrating these detection tools more widely. Ideally, you introduce an element that only humans can do, e.g., you have to pick up your price somewhere in-person. Btw, note that these bots can easily be designed to find ways around the most common detection tactics such as Captcha’s, timed responses and postcode and IP recognition. Believe me, way less code than you suspect is needed to do this...

Schneier on Security
The Manuscript: a technothriller written by someone who understands technology – Cory Doctorow's MEMEX

Detecting Phishing Emails - Schneier on Security

Schneier on Security
Detecting Phishing Emails - Schneier on Security

Schneier on Security