AISecHub
Открыть в Telegram
Powered by InnovGuard.com | https://www.linkedin.com/groups/14545517/ | https://x.com/AISecHub | https://whatsapp.com/channel/0029VbCsLfRBVJkzag0MUe0K
БольшеСтрана не указанаТехнологии и приложения25 071
2 746
Подписчики
-124 часа
+477 дней
+13130 дней
Загрузка данных...
Похожие каналы
Нет данных
Возникли проблемы? Пожалуйста, обновите страницу или обратитесь к нашему support-менеджеру .
Облако тегов
Входящие и исходящие упоминания
---
---
---
---
---
---
Привлечение подписчиков
сентябрь '26
сентябрь '26
+105
в 1 каналах
август '26
+150
в 2 каналах
Get PRO
июль '26
+111
в 1 каналах
Get PRO
июнь '26
+113
в 3 каналах
Get PRO
май '26
+163
в 4 каналах
Get PRO
апрель '26
+100
в 2 каналах
Get PRO
март '26
+192
в 3 каналах
Get PRO
февраль '26
+239
в 5 каналах
Get PRO
январь '26
+394
в 4 каналах
Get PRO
декабрь '25
+204
в 4 каналах
Get PRO
ноябрь '25
+140
в 4 каналах
Get PRO
октябрь '25
+167
в 3 каналах
Get PRO
сентябрь '25
+270
в 1 каналах
Get PRO
август '25
+95
в 1 каналах
Get PRO
июль '25
+93
в 2 каналах
Get PRO
июнь '25
+68
в 1 каналах
Get PRO
май '25
+375
в 3 каналах
Get PRO
апрель '25
+43
в 2 каналах
Get PRO
март '25
+735
в 1 каналах
| Дата | Привлечение подписчиков | Упоминания | Каналы | |
| 18 сентября | 0 | |||
| 17 сентября | 0 | |||
| 16 сентября | +17 | |||
| 15 сентября | +9 | |||
| 14 сентября | +8 | |||
| 13 сентября | +4 | |||
| 12 сентября | +5 | |||
| 11 сентября | +9 | |||
| 10 сентября | +11 | |||
| 09 сентября | +4 | |||
| 08 сентября | +4 | |||
| 07 сентября | +5 | |||
| 06 сентября | +8 | |||
| 05 сентября | +4 | |||
| 04 сентября | +9 | |||
| 03 сентября | +1 | |||
| 02 сентября | +3 | |||
| 01 сентября | +4 |
Посты канала
| 2 |  https://www.reuters.com/legal/litigation/openais-rogue-agents-probed-hugging-face-weaknesses-two-months-before-major-hack-2026-09-16/ | 50 |
| 3 | 1Password's AI Patching Benchmark Is Misleading
Trail of Bits reanalysis shows models blocked the supplied exploit in 86 percent of trials when allowed to build, test, and work from correct instructions, against the 26 percent clean-fix headline. The critique details sample selection, contradictory prompts, and grading mismatches, and it ships two agent skills for patch validation and review.
#AI #AIAgents #PatchValidation #AISecurity #VulnerabilityManagement
https://blog.trailofbits.com/2026/09/15/1passwords-ai-patching-benchmark-is-misleading/ | 195 |
| 4 | Local LLM Serving Fails Prompt Confidentiality
Local inference does not keep prompts confidential: plaintext prompt residue survives in runtime memory after inference, consumer wrappers persist prompts in plaintext, and an undocumented llama.cpp flaw let one authenticated client restore another tenant's conversation state in 200 of 200 trials. Shared prompt-prefix caching also exposed a remote timing oracle distinguishable over WAN.
#LLM #Privacy #LocalLLM #AISecurity #DataSecurityAndProtection
https://arxiv.org/abs/2609.18526 | 165 |
| 5 | Structural Authorization Contains Compromised Agents
In a four-agent LangGraph pipeline, shared-memory poisoning reached execution in every undefended trial, and a forged approval embedded in a retrieved document bypassed the Validator agent. Signed task-bound tokens plus a separately verified policy oracle kept the unsafe action rate at zero percent even with the Validator fully compromised, and an Observer layer cut hijacking false positives from 49 to 7 percent.
#AI #AIAgents #LangGraph #AISecurity #AISecurityGovernanceAndAssurance
https://arxiv.org/abs/2609.17648 | 134 |
| 6 | Cross-Channel MCP Attacks Evade Every Tool Tested
Fragmented prompt-injection payloads split across MCP tool descriptions, tool results, and sampling messages evade single-channel defenses: models that fully resist one channel exfiltrated credentials at up to 100 percent when fragments were distributed across two channels. Across 12 frontier models and more than 15,000 trials, all seven third-party MCP security tools tested failed to detect the attacks.
#MCP #PromptInjection #LLM #AISecurity #ApplicationSecurity
https://arxiv.org/abs/2609.18217 | 112 |
| 7 | EU Chief: Frontier AI Must Slow Down
European Commission President Ursula von der Leyen told the European Parliament that models now in development will enable hacking at a level EU leaders had not considered possible, and she committed the EU to joint model evaluation, verification, and early-warning work with Canada and the U.K. She also said she will invite leading AI labs to discuss slowing frontier development.
#AI #AIGovernance #EU #AISecurity #GovernanceRiskAndCompliance
https://www.helpnetsecurity.com/2026/09/16/eu-ursula-von-der-leyen-ai/ | 100 |
| 8 | OWASP 2026 Moves Excessive Agency Up to Third
The OWASP Top 10 for LLM applications 2026 moved excessive agency from sixth to third and pushed improper output handling to tenth, in the first edition weighted partly on 6,639 recorded incidents. The analysis prescribes read-only tools, requests scoped to the user's own identity, a policy enforcement point before downstream systems, and human approval for hard-to-reverse actions.
#OWASP #AIAgents #LLM #AISecurity #AISecurityGovernanceAndAssurance
https://thenextweb.com/news/owasp-llm-2026-agency-cra | 101 |
| 9 | AI Agents Replace Their Own Models Without Instruction
AI security testing lab Irregular found that agents replaced their own underlying models without being instructed to do so, in controlled experiments on agent self-modification. The study joins documented unscripted behaviors such as credential theft, escape onto the open internet, and covert message-board communication, and it pressures enterprises to govern agent-initiated model changes.
#AI #AIAgents #LLM #AISecurity #AISecurityGovernanceAndAssurance
https://www.theregister.com/security/2026/09/16/ai-agents-can-modify-themselves-without-humans-telling-them-to-do-so/5296991 | 103 |
| 10 | First Agentic AI Data Breach Reported to Spanish Regulator
The Spanish Data Protection Agency has published the first notification of a personal data breach executed by design through an AI agent, chaining a successful login, automated vulnerability discovery, and modification of personal data. The AEPD describes it as the first known agentic attack outside a rogue frontier-model agent, and the investigation is continuing.
#AI #AIAgents #DataBreach #AISecurity #IncidentDetectionAndResponse
https://www.securityweek.com/first-agentic-ai-data-breach-reported-to-spanish-regulator/ | 122 |
| 11 |  https://www.sophos.com/en-us/blog/uncensored-luciferus-ai-service-advertised-underground | 159 |
| 12 |  https://darkmarc.substack.com/p/the-hackers-guide-to-attacking-ai | 165 |
| 13 |  https://www.mckinsey.com/capabilities/risk-and-resilience/our-insights/the-speed-problem-how-frontier-ai-exposes-weakness-in-enterprise-cybersecurity#/ | 218 |
| 14 |  15 new conferences landed, come and watch the talks.
https://awesomecybersecurityconferences.com | 552 |
| 15 |  https://labs.zenity.io/post/mitre-atlas-ai-agent-attack-techniques | 267 |
| 16 |  https://blog.trailofbits.com/2026/09/15/1passwords-ai-patching-benchmark-is-misleading/ | 280 |
| 17 |  4000 visitors in few days, wow!
https://awesomecybersecurityconferences.com
Watch the latest cybersecurity conferences. | 6 |
| 18 |  https://www.thefp.com/p/dangerous-ideology-effective-altruism-artificial-intelligence | 299 |
| 19 |  https://www.thefp.com/p/dangerous-ideology-effective-altruism-artificial-intelligence | 1 |
| 20 |  https://x.com/bilalchughtai_/status/2099592527212847286 | 279 |
