Telegram RegisterThe public register of Telegram
Telegram profile photo for Борис_ь с ml

Channel

Борис_ь с ml

@borismlsec

On this record: Growth · Engagement · Reactions · Stars · Posts · Citations · Cite this entry

2,369subscribers

+115 since we began measuring on 6 August 2026

Risers and fallers across the register · movement among entries of 1,000–3,162.

Register entry

Telegram ID-1002034663817
TypeChannel
Username@borismlsec
CreatedBetween 1 November 2023 and 31 May 2024 — estimated from Telegram’s id allocation, not measured. How this range is calculated.
First recorded6 August 2026
Last confirmed live8 September 2026
Measurements held12
Confirmed unchanged1 time, most recently 8 September 2026
On Telegramt.me/borismlsec

Growth

2,2532,3692,3116 August 2026 — 2,254 subscribers6 August 2026 — 2,253 subscribers10 August 2026 — 2,254 subscribers13 August 2026 — 2,261 subscribers16 August 2026 — 2,267 subscribers19 August 2026 — 2,322 subscribers23 August 2026 — 2,333 subscribers25 August 2026 — 2,345 subscribers28 August 2026 — 2,340 subscribers31 August 2026 — 2,346 subscribers3 September 2026 — 2,356 subscribers8 September 2026 — 2,369 subscribers6 August 20268 September 2026
12 measurements spanning 33 days, net +115. Dots are measurements; the straight line between them is drawn to join them, not to claim we know the path taken in between — snapshots are recorded only when a count changes, so gaps mean “no change observed”, never “interpolated”. The vertical axis spans 2,236–2,386 and does not start at zero.
Measurement log — every subscribers count we have recorded
Measured (UTC)SubscribersChange
8 Sept 2026, 20:562,369+13
3 Sept 2026, 23:012,356+10
31 Aug 2026, 03:262,346+6
28 Aug 2026, 12:132,340-5
25 Aug 2026, 21:232,345+12
23 Aug 2026, 00:242,333+11
19 Aug 2026, 20:142,322+55
16 Aug 2026, 17:142,267+6
13 Aug 2026, 11:482,261+7
10 Aug 2026, 04:552,254+1
6 Aug 2026, 20:412,253-1
6 Aug 2026, 12:012,254first reading

Engagement

21 posts held, back to 13 January 2026the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 2 pages of Telegram’s post history, 20 posts per page.

Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 21 posts for this entry, the most recent from 6 August 2026. An engagement rate over an empty window would be a number about nothing.

Reaction mix

327 reactions across 21 posts, in 15 distinct kinds. The most used accounts for 36.7% of them.

Every reaction kind recorded on the sample, most used first
ReactionCountShareShare, drawn
👍12036.7%
🔥8124.8%
7422.6%
🤝133.98%
🤣103.06%
😁82.45%
🕊61.83%
🖕30.917%
🤩30.917%
20.612%
😎20.612%
🤨20.612%
💯10.306%
🤔10.306%
🥰10.306%

No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.

Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.

Coverage. Reactions were read on 21 of the 21 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 327 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.

Measured over the 21 most recent posts we hold, published 13 January 2026 to 6 August 2026, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.

Telegram Stars

Stars received
29
across the posts below
Posts paid on
8
of 21 we hold a reading for · 38%
Most on one post
14
single highest reading

A paid reaction is a reader spending Telegram Stars — bought with money — on a post by @borismlsec. Telegram publishes the count on the public post preview alongside ordinary reactions, and this register reads it there. It is the only figure on this site that measures money moving rather than attention.

Stars are not reactions, and the two are never added. They are rendered in the same strip on Telegram and counted in the same shape, but one is a tap and the other is a purchase. The reaction totals and the engagement rate elsewhere on this page exclude every figure in this section, and no rate here is computed against a reaction count.

This is not revenue, and we publish no currency figure. What a Star costs a reader and what it pays a channel are different numbers, Telegram takes a share we cannot observe, and the terms have changed. Converting a Star count into money would be an estimate dressed as a measurement, so the count is where we stop.

Counted over the 21 most recent posts we hold for this entry, published 13 January 2026 to 6 August 2026. Star counts above 1,000 reach us in Telegram’s short form and carry the same three-significant-figure rounding as everything else on this page.

Recent posts

6 Aug 2026, 12:27 UTC242 views5 reactionsread 7 August 2026
Forwarded from @mlsecfeedFile

NOOA 27 июля 2026 года NVIDIA представила NOOA — открытый исследовательский фреймворк для создания AI-агентов как обычных Python-объектов. Методы класса задают возможности агента, поля хранят типизированное состояние, а LLM выполняет действия, генерируя Python-код и работая с живыми объектами. С точки зрения безопасности NOOA интересна сочетанием типизированных интерфейсов, детерминированных проверок и прослеживаем

🔥3🤔1🤩1

27 Jul 2026, 21:25 UTC940 views5 reactionsread 7 August 2026
File

пост с разбором МУ КБ AI 2.0 от Сбера

👍32

27 Jul 2026, 21:25 UTC≈2,770 views23 reactionsread 7 August 2026

Posted without readable text

👍10🔥10🤩2😁1

8 Jul 2026, 14:38 UTC988 views14 reactionsread 7 August 2026
Photo

Жили не тужили, да агентов смастерили. Значит ли это что-то для SOC? #иб_для_ml Есть мнение, что AI Security в некоторой степени хайпово: угрозы есть, но серьезные процессы кибербезопасности живут по прежним правилам. Так ли это?.. На уровне целей ИБ ответ да: защищаем конфиденциальность, целостность, доступность и устойчивость. На уровне операционных и технических деталей ответ нет. Кибербезопасность меняется, ког

👍9🔥41

17 Jun 2026, 20:55 UTC≈1,150 views12 reactions1 Starread 7 August 2026
Forwarded from @abstractDLPhoto

Photo, posted without a caption

🤣8😁3💯1

3 Jun 2026, 19:23 UTC≈3,490 views8 reactionsread 7 August 2026
Photo

OWASP State of Agentic AI Security and Governance v2.01 #иб_для_ml Прочитал большой отчет OWASP по безопасности и управлению агентными ИИ-системами, который вышел 2 дня назад. Отвлечемся немного от сложных концепций и посмотрим на индустрию с позиции хеликоптер-хеликоптер, пара кофер - пара кофер... Главная мысль: агентная ИИ-система — это композиция из модели, агента, памяти, источников контекста, инструментов, пр

👍5🤣2🔥1

27 May 2026, 06:42 UTC≈1,400 views16 reactionsread 7 August 2026
Photo

Зонд безопасности #иб_для_ml Механизмы безопасности AI-агентов требуют развития - потому что обойти их уже стало если не спортивным интересом любого пользователя, то абсолютно очевидным обстоятельством для любого злоумышленника точно. Все начинают с блэклистов и оценок близости, потом приходят к BERT-моделям или легким LLM-классификаторам. Я давно слышу, что гардрейлы - это не все, и они ненадежны. Действительно, э

7👍7🔥2

9 May 2026, 08:16 UTC≈1,200 views52 reactions3 Starsread 7 August 2026
Photo

С Днем Победы! Память о тех воинах, что превратились в белых журавлей, вплелась навсегда в дух нашего народа. С гордостью несем воинскую волю сегодня и всегда.

31🤝7👍4🕊4🖕3🤨2🔥1

23 Apr 2026, 20:15 UTC≈1,500 views30 reactionsread 7 August 2026
Photo

[un]prompted 2026 - интересное #иб_для_ml Добрался наконец до докладов с конференции [un]prompted. Она прошла 3–4 марта в Сан-Франциско, и посвящена целиком AI Security. Выступали все известные вендоры - от Anthropic до Zenity, а программа была разбита на 6 треков: 1. building secure AI systems 2. attacking AI systems 3. using AI for offensive security 4. using AI for defensive security 5. strategy/governance 6. pra

🔥22👍4😎21🕊1

3 Apr 2026, 17:08 UTC≈1,700 views16 reactionsread 7 August 2026
Photo

Саморазвивающиеся агенты и их угрозы #иб_для_ml Сегодня много шума вокруг Ouroboros - агента, эволюционирующего самостоятельно. Это новое для 2026 года явление, отличающееся от обычных AI-агентов и OpenClaw. Что такое саморазвивающиеся агенты? Предлагаю понять суть в сравнении. 1. Все началось с AI-агентов - кода с промптами, написанного человеком. Это управление состояниями, сессиями, обработкой сигналов и инструм

9👍7

18 Mar 2026, 19:29 UTC≈1,380 views10 reactionsread 7 August 2026
Photo

Почему большинство компаний не готовы к реальной атаке? #иб Как известно, в кибербезопасности можно бесконечно улучшать технологии, процессы и инструменты. Но как понять, что твоя организация готова к атаке? Ждать боевого инцидента можно долго, и не факт, что его получится отразить... Необходимо иметь возможность в условиях, приближенным к реальным, проверить свою киберустойчивость к атакам, эксплуатирующим не тольк

4🔥4🕊1😁1

Showing the 12 most recent of 21 posts we hold for @borismlsec. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.

Stars beside a post are paid reactions — Telegram Stars, bought with money and spent on that post. They are a different unit from reactions and are never added to them, here or anywhere else on this page.

Forward network

Republished by

Channels on the register that have forwarded this channel's posts into their own feed.

Republishes

Channels on the register whose posts this channel has forwarded.

Built only from forwarded posts we have actually read, on both sides. Coverage is early and deliberately incomplete: a missing link means we have not read the post that would prove it, never that the relationship does not exist. Counts are distinct forwarded posts observed, so they only ever go up as we read more.

Mentions

Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.

Named by

Channels on the register whose posts name this channel's handle.

A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.

Cite this entry

A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 8 September 2026 — this entry's latest reading, not the date you are reading this.

“Борис_ь с ml” (@borismlsec), 2,369 subscribers as measured 8 September 2026. Telegram Register, tgregister.com/channel/borismlsec.

Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.