DCWebGuy

Malware hunter/analyst. PCAP denizen. Old-school webdev. (re-)Tweets mainly infosec IOCs, plus some politics and science. Consilience bias. I hate ideologies.

[DCWebGuy @DCWebGuy]

This is important, you should watch it. Knowledge is going public.

[ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ 🛡️ @DanielMiessler]

https://t.co/YgsGdPRvAI

[Bridget D 🐝🌷🪻⚘️🦋 @ZoeyCatBell]

Today's 82nd anniversary of D-Day comes with the unveiling of a new national tribute to those who changed the course of World War II.

The National Memorial of Military Ascent (NMMA) is a tribute to the U.S. Army Rangers who scaled the 100-foot cliffs of Pointe du Hoc during the D-Day invasion of Normandy in World War II. Located in Grafton, Illinois, the memorial utilizes the steep limestone bluffs along the Mississippi River to visually recreate this historic 1944 climb.
#Dday
#OmahaBeach
#WW2
#LestWeForget

[UnveiledChina @Unveiled_ChinaX]

A careless code blunder just blew the lid off Beijing’s multi-million dollar AI propaganda operation targeting the West. France's digital interference watchdog, Viginum, has officially exposed "Fawn Mianju," a covert network of 13 multilingual fake news sites running on advanced automation and generative AI. The sophisticated network was completely compromised after a computer engineer working as a Senior Project Manager at China's state-run CGTN Digital accidentally left his login credentials exposed in the code.

This operation, which expanded on findings first uncovered by U.S. cybersecurity firm Graphika in 2025, operated with deep financial backing. The domains were registered in Beijing, hosted on Alibaba Cloud, and utilized expensive infrastructure alongside paid plugins to artificially manipulate search engine rankings. Using digital keys linked directly to AI language models, the network automatically scraped CGTN articles, lightly rewrote them, and republished over 2,300 articles, often within less than an hour of the original state media broadcast.

Sites like the French-language "Actu Méridien" were weaponized to manipulate public opinion across 89 countries, heavily targeting Western audiences and Francophone African youth. The articles aggressively peddled pro-Beijing narratives, painting China as the undisputed leader of the Global South and green energy transition while explicitly telling Western readers that aligning with Chinese interests would bring them massive benefits.

Despite the cutting-edge tech and heavy state funding, the operation was an organic flop. The articles struggled to breach 15,000 views, with nearly 40 percent of its top social media engagement traced back to fake accounts in Burundi whose sole purpose was to artificially inflate the content. While the reach was limited, French authorities warn that the operation exposes Beijing’s rapidly escalating capability to launch fully automated, stealth disinformation campaigns designed to quietly erode Western democratic alignment.

#Disinformation #CyberSecurity #France #China #AIPropaganda #Geopolitics #Viginum #NationalSecurity

[Rohan Paul @rohanpaul_ai]

"I don't prompt Claude anymore. I have loops running that prompt Claude and figuring out what to do. My job is to write loops. And this is transition we're going to see for the rest of the year."

- Boris Cherny, head of Claude Code at Anthropic.

[Jeremy Padawer @JeremyCom]

The odds of Nithya Raman receiving 40% of the vote yesterday are “LESS LIKELY than picking ONE GRAIN OF SAND on Earth dozens of times in a row.” I believe elections tend to be fair. Someone help me make sense of math that seems impossible…

I ASKED CHATGPT -
“What is the statistical likelihood that 40% of votes from a “new batch” of ballots go to a candidate who received 24% of votes from all other batches that represented 95% of counted electorate. Give me a % odds.”

The Answer (Part 1) -
“Assuming the candidate’s “true” share is 24%, the odds that a random new batch lands at 40% or higher depends on batch size:
50 ballots
0.88%
100 ballots
0.028%
200 ballots
0.00004%
500 ballots
~0.00000000000018%
1,000 ballots
~0.0000000000000000000000000035%”

My follow up -
“Assume 40,000 ballots. Are the odds one in a billion? One in a trillion? Worse? This seems to be happening in Los Angeles Mayor’s race between Mayor Bass, Spencer Pratt and Nithya Raman.”

The Answer (Part 2) -
“If the 40,000-ballot batch were drawn from the same population that produced 24% support in the other 95% of votes, then seeing 40% support in that batch would be far beyond “one in a billion” or “one in a trillion.”

75 standard deviations is in an entirely different universe.

The probability is approximately:

~10⁻¹²²⁰

or about

1 chance in 10¹²²⁰

That’s a number with roughly 1,220 zeros after the 1.

Statistically, if the batch were truly a random sample of the same electorate, the odds are so small that statisticians would effectively treat the event as impossible. The usual conclusion would not be “wow, what a lucky fluctuation,” but rather that the batch is not representative of the earlier ballots—for example, it came from a different geographic area, voting method, demographic group, or subset of voters.

So yes: much worse than one in a billion, much worse than one in a trillion, and vastly smaller than any probability encountered in ordinary statistical analysis.”

My follow up -
“More grains of sand on earth than the likelihood of this?”

The Answer (Part 3) -
“Yes. Much, much more.

Estimated grains of sand on Earth are often put around 10¹⁸ to 10²⁰.

Your odds example was roughly:

1 in 10¹²²⁰

So this is not just “less likely than picking one grain of sand on Earth.”

It’s more like picking the right grain of sand on Earth correctly over and over again dozens of times in a row.”

Sincerely,
Jeremy Padawer
https://t.co/POrFyAfNhH

@spencerpratt @BoredElonMusk @Hotshot_Movie @415FirePhoto
#losangeles #la #fyp #mayor

[stephanie wakefield @stephwakefield_]

Here's a draft excerpt from our film project THE WILD CITY, chapter on contemporary warfare. Needs more reality melt - suggestions would be welcome

[Legal Mindset @TheLegalMindset]

Translation: Sorry, we were accidentally transparent, we meant to edit the files to solely support Bricks and Minifigs.

[International Cyber Digest @IntCyberDigest]

❗️Update: Bright Data calls itself "inherently safer and more ethical."

But its SDK turns Samsung/LG TVs into scraping exit nodes with no signing, no auth, no attestation. Less secure than typical malware C2 according to a recent analysis.

And how is routing scraping through residential IPs to dodge blocks "ethical"?

[Miles Cranmer @MilesCranmer]

This is an insane paper and I love it

https://t.co/DP8OR5NJf2

[solst/ICE of Astarte @IceSolst]

Claude code’s /security-review is just a Skill, and the whole prompt is in this repo

It’s p generic and imo you can tailor it to each repo to language you’re scanning to get better results

https://t.co/1a4puZSASL

[\newcommand{\femb0t}{ @__femb0t]

Found the best tweets on this website

[John Sailer @JohnDSailer]

NEW: a report from Vanderbilt and WashU just dropped, taking on the "state of scholarship in the humanities and social sciences," a big topic among critics of higher ed.

Read along w/ me 🧵

[International Cyber Digest @IntCyberDigest]

❗️🚨 An Israeli company has backdoored hundreds of millions of households through countless Smart TV apps, and they're quietly turning Samsung and LG TVs into exit nodes for AI web-scraping. Your TV is relaying strangers' web traffic from your home IP, your bandwidth, your address attached to whatever those scraping jobs touch.

Roku, Fire TV and Google TV banned the practice. Samsung and LG didn't. The culprit is Bright Data's proxy SDK, which rides inside Tizen and webOS apps, 200+ on webOS alone. Datacenter IPs get blocked, home IPs don't.

Include Security reverse-engineered the SDK and found its relay protocol has no message signing, authentication, or device attestation. Their words: less secure than typical malware command-and-control.

To make things worse, they found that in iOS the relay tunnel binds straight to the physical network interface, so it routes around any VPN the user is running.

Bright Data's config also ships per-country tiers. Devices in Uzbekistan and Oman are cleared to relay down to 1% battery, with data caps up to 60x the worldwide default.

Before the BaCkDoOrEd replies land: technically you agreed. In practice you were enrolled into a global proxy network you were never given the information to refuse. And these exit nodes drag down your IP's reputation, potentially leaving you with blocks from providers.

[DCWebGuy @DCWebGuy]

@GodSpawned @Math_files Thank you for posting this link!

[Mandiant (part of Google Cloud) @Mandiant]

🚨 UNC3753 is targeting US law firms using vishing and RMM tools for data extortion.

In instances linked to UNC3753, individuals posing as IT technicians attempted direct data theft using physical, in-person access.

Read more & get IOCs ➔ https://t.co/0SDAcovfSY

[Nicolas Hulscher, MPH @NicHulscher]

BREAKING: ADVANCED ALZHEIMER’S PATIENT REGAINED SPEECH, MEMORY, AND BLADDER CONTROL AFTER SINGLE PSILOCYBIN DOSE

An 80-year-old woman with advanced Alzheimer’s — who had barely spoken for YEARS — experienced RAPID and SUSTAINED improvement after taking 5g of psilocybin mushrooms.

During the acute phase, she entered a prolonged deep sleep-like state with profuse sweating.

~19 hours later, she spontaneously started talking again for HOURS — sharing detailed autobiographical memories she hadn’t expressed in years.

Over the following days, her family reported improved memory, walking, emotional connection, speech, and regained bladder control.

After 1 month, bladder control REMAINED RESTORED, and she was still functionally improved compared with baseline.

While this is just one published case report, the implications are enormous given that there are currently NO approved medications known to produce effects like this in advanced Alzheimer’s.

These findings urgently need replication. For millions watching a parent or loved one disappear to Alzheimer’s, even the possibility of restoring lost function warrants serious scientific investigation.

[DCWebGuy @DCWebGuy]

@EMBurlingame Bought, looking forward to reading it.

[Outpost Studios @OutpostStudios]

@JDVance The shocking True story behind the murder of Henry Nowak.

[Nate Silver @NateSilver538]

It's hard to overstate how much of an outlier California is for its slow vote-counting relative to literally any other state or almost any other industrialized democracy.

[Cyber Security News @The_Cyber_News]

🚨 Cisco SD-WAN Flaw Exploited in the Wild to Execute Arbitrary Commands as Root User

Source: https://t.co/VkLDwE2EsI

Cisco has disclosed a high-severity vulnerability in its Catalyst SD-WAN Manager that is actively being exploited in the wild, allowing attackers to execute arbitrary commands with root privileges.

The flaw stems from insufficient sanitization of user-supplied input during the processing of uploaded files. An authenticated attacker can exploit this weakness by uploading a specially crafted file, which triggers command injection and enables privilege escalation to the root user.

Once root access is obtained, attackers can fully compromise the SD-WAN management plane, manipulate configurations, and potentially impact connected edge devices.

#cybersecuritynews #vulnerabilitynews