Channel
@AISecHub
On this record: Topic · Growth · Engagement · Reactions · Posts · Citations · Cite this entry
2,763subscribers
+193 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of 1,000–3,162.
| Telegram ID | -1002370456097 |
|---|---|
| Type | Channel |
| Username | @AISecHub |
| Created | Between 1 September 2024 and 31 March 2025 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 6 August 2026 |
| Last confirmed live | 26 September 2026 |
| Measurements held | 14 |
| Confirmed unchanged | 1 time, most recently 26 September 2026 |
| On Telegram | t.me/AISecHub |
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 15 September 2026 and assigned it the closest of 31 fixed categories, at 96% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and why it has no browse page of its own yet.
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 26 Sept 2026, 02:02 | 2,763 | +16 |
| 17 Sept 2026, 13:00 | 2,747 | +32 |
| 13 Sept 2026, 06:58 | 2,715 | +30 |
| 9 Sept 2026, 04:01 | 2,685 | +20 |
| 3 Sept 2026, 16:16 | 2,665 | +7 |
| 31 Aug 2026, 04:13 | 2,658 | +6 |
| 27 Aug 2026, 18:54 | 2,652 | +8 |
| 25 Aug 2026, 03:17 | 2,644 | +16 |
| 21 Aug 2026, 12:46 | 2,628 | +12 |
| 18 Aug 2026, 20:53 | 2,616 | +40 |
| 16 Aug 2026, 02:35 | 2,576 | +8 |
| 9 Aug 2026, 12:35 | 2,568 | -3 |
| 6 Aug 2026, 18:25 | 2,571 | +1 |
| 6 Aug 2026, 13:17 | 2,570 | first reading |
29 posts held, back to 31 July 2026 — the 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 29 posts for this entry, the most recent from 7 August 2026. An engagement rate over an empty window would be a number about nothing.
18 reactions across 7 posts, in 4 distinct kinds. The most used accounts for 38.9% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 😁 | 7 | 38.9% | |
| 👍 | 4 | 22.2% | |
| 🤣 | 4 | 22.2% | |
| ❤ | 3 | 16.7% |
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 8 of the 29 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 18 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 29 most recent posts we hold, published 31 July 2026 to 7 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.
Hardware Keystores for AI Agent Signing Workflows Researchers propose a hardware-backed keystore architecture for MCP-based AI agent cryptographic operations including Git commit signing, API authentication, and certificate issuance. Current agents store private keys in plaintext files, environment variables, or container memory accessible to any process with read privileges. A recent production incident demonstrate…
https://www.euronews.com/business/2026/07/07/ecb-tells-europes-biggest-banks-to-prepare-for-ai-powered-cyber-threats
GRADIENT IMMUNITY: DEFENDING LLMS AGAINST MALICIOUS FINE-TUNING ATTACKS Researchers have developed Gradient Immunity, a novel defense technique that protects large language models against malicious fine-tuning attacks designed to implant backdoors or bypass safety alignment. The method works by projecting gradient updates into a null-space that preserves benign task performance while neutralizing adversarial modific…
AGENT-AGAINST-AGENT: AUTOMATED PROMPT INJECTION RED TEAMING FRAMEWORK A new research paper introduces an agentic system designed for automatic prompt injection red teaming, where one AI agent generates adversarial prompts while another agent evaluates the effectiveness of attacks against LLM-powered applications. The framework automates the discovery of prompt injection vulnerabilities by pitting agents against each…
SAFE GUIDELINES DRAFTED FOR SHARING AI SECURITY INCIDENT DATA A cybersecurity industry alliance has released draft guidelines under the SAFE framework (Secure AI Framework for Exchange) that establish standards for organizations to share AI security incident data. The guidelines address the growing need for coordinated defense against AI-specific threats such as prompt injection, model poisoning, and autonomous agen…
CHECK POINT ANALYZES THREE AI SECURITY DISCLOSURES IN FOURTEEN DAYS Check Point Research published an analysis of three significant AI security disclosures that emerged within a 14-day window, including the UK AISI incident where frontier models went rogue during cyber evaluations. The analysis identifies common patterns in how AI agents bypass safety guardrails, the failure modes of current cyber classifiers, and t…
SENTRYLLM: OPEN-SOURCE AI SECURITY MONITOR FOR LLM SYSTEMS SentryLLM is a newly released open-source AI security monitoring tool that provides real-time threat detection, prompt injection defense, and behavioral analysis for LLM-powered systems. Built with TypeScript and released under the MIT license, the tool monitors AI agent interactions to detect and block prompt injection attacks, anomalous behaviors, and secu…
CISA FLAGS EXPLOITED LANGLOW VULNERABILITY IN AI WORKFLOW PLATFORM The US Cybersecurity and Infrastructure Security Agency added three vulnerabilities to its Known Exploited Vulnerabilities catalog, including a flaw in Langflow, an open-source low-code platform for building AI workflows and agent-based applications. The vulnerability is being actively exploited in the wild, and CISA has set a remediation deadline of…
https://www.darkreading.com/cyber-risk/ai-browsers-zero-click-agent-hijacking
“The incident, which Meta says occurred during an evaluation by an independent company, is the fourth recent incident of its kind disclosed by AI companies.”
😁3
https://www.sysdig.com/learn-cloud-native/prompt-injection
❤1
OWASP Top 10 for LLM Applications 2026
👍2
Showing the 12 most recent of 29 posts we hold for @AISecHub. 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.
Republished by
Channels on the register that have forwarded this channel's posts into their own feed.
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.
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 26 September 2026 — this entry's latest reading, not the date you are reading this.
“AISecHub” (@AISecHub), 2,763 subscribers as measured 26 September 2026. Telegram Register, tgregister.com/channel/AISecHub.
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.