Not so hidden hidden layer. ✨
I really loved going out Like this and am proud that I did it. ✨
Would you join me on a layered walk under my lead. 😏
#raingear #gearhead #hiddenlayer
I really loved going out Like this and am proud that I did it. ✨
Would you join me on a layered walk under my lead. 😏
#raingear #gearhead #hiddenlayer
August 24, 2026 at 7:47 AM
Not so hidden hidden layer. ✨
I really loved going out Like this and am proud that I did it. ✨
Would you join me on a layered walk under my lead. 😏
#raingear #gearhead #hiddenlayer
I really loved going out Like this and am proud that I did it. ✨
Would you join me on a layered walk under my lead. 😏
#raingear #gearhead #hiddenlayer
HiddenLayer підняв 100 мільйонів доларів на захист самих AI систем.
У вересні 2026 компанія HiddenLayer закрила раунд Series B на суму 100 мільйонів доларів. Раунд очолив фонд Delta-v Capital, до угоди доєднались Ten Eleven Ventures, Morgan Stanley […]
[Original post on social.vir.group]
У вересні 2026 компанія HiddenLayer закрила раунд Series B на суму 100 мільйонів доларів. Раунд очолив фонд Delta-v Capital, до угоди доєднались Ten Eleven Ventures, Morgan Stanley […]
[Original post on social.vir.group]
September 18, 2026 at 2:21 PM
HiddenLayer підняв 100 мільйонів доларів на захист самих AI систем.
У вересні 2026 компанія HiddenLayer закрила раунд Series B на суму 100 мільйонів доларів. Раунд очолив фонд Delta-v Capital, до угоди доєднались Ten Eleven Ventures, Morgan Stanley […]
[Original post on social.vir.group]
У вересні 2026 компанія HiddenLayer закрила раунд Series B на суму 100 мільйонів доларів. Раунд очолив фонд Delta-v Capital, до угоди доєднались Ten Eleven Ventures, Morgan Stanley […]
[Original post on social.vir.group]
HiddenLayer lands $100M for AI security 💰
HiddenLayer raised $100M for its AI security tools, confirming that the market for protecting models and agents from attacks like prompt injection is now very real and rapidly growing.
HiddenLayer raised $100M for its AI security tools, confirming that the market for protecting models and agents from attacks like prompt injection is now very real and rapidly growing.
September 2, 2026 at 3:13 PM
HiddenLayer lands $100M for AI security 💰
HiddenLayer raised $100M for its AI security tools, confirming that the market for protecting models and agents from attacks like prompt injection is now very real and rapidly growing.
HiddenLayer raised $100M for its AI security tools, confirming that the market for protecting models and agents from attacks like prompt injection is now very real and rapidly growing.
HiddenLayer Partners with Databricks to Enhance AI Security Across Enterprise Workloads#United_States#Austin#Databricks#AI_Security#HiddenLayer
HiddenLayer Partners with Databricks to Enhance AI Security Across Enterprise Workloads
HiddenLayer has joined Databricks' Unity AI Gateway to strengthen AI security for enterprises. This collaboration aims to protect AI systems as they scale and evolve.
third-news.com
June 29, 2026 at 2:58 PM
HiddenLayer Partners with Databricks to Enhance AI Security Across Enterprise Workloads#United_States#Austin#Databricks#AI_Security#HiddenLayer
hiddenlayer.com/research/sha...
攻撃方法はこう。翻訳して読んでね
攻撃方法はこう。翻訳して読んでね
HiddenLayer Research | ShadowLogic
The HiddenLayer SAI team has discovered a novel method for creating backdoors in neural network models dubbed ‘ShadowLogic’.
hiddenlayer.com
October 18, 2024 at 7:07 AM
hiddenlayer.com/research/sha...
攻撃方法はこう。翻訳して読んでね
攻撃方法はこう。翻訳して読んでね
HiddenLayer nabs $100M as enterprises rush to secure their AI deployments
HiddenLayer nabs $100M as enterprises rush to secure their AI deployments
HiddenLayer has raised a $100M Series B from Delta-v Capital, Ten Eleven Ventures, Morgan Stanley, Microsoft's M12, Booz Allen Hamilton, and others.
techcrunch.com
September 2, 2026 at 3:03 PM
HiddenLayer nabs $100M as enterprises rush to secure their AI deployments
Need a jailbreak? Just add `=coffee`.
This research shows that careful analysis of model training data reveals token sequence that can flip attack detection.
Good lord this technology is goofy.
This research shows that careful analysis of model training data reveals token sequence that can flip attack detection.
Good lord this technology is goofy.
EchoGram: The Hidden Vulnerability Undermining AI Guardrails
HiddenLayer unveils EchoGram, a new attack technique that manipulates AI guardrails protecting LLMs like GPT-4, Claude, and Gemini.
hiddenlayer.com
December 7, 2025 at 9:33 PM
Need a jailbreak? Just add `=coffee`.
This research shows that careful analysis of model training data reveals token sequence that can flip attack detection.
Good lord this technology is goofy.
This research shows that careful analysis of model training data reveals token sequence that can flip attack detection.
Good lord this technology is goofy.
HiddenLayer has raised $100M in Series B funding led by Delta-v Capital, with participation from Ten Eleven Ventures, Morgan Stanley, M12 and Booz Allen Ventures.
The Austin startup develops cybersecurity technology for agentic, generative and predictive AI applications.
The Austin startup develops cybersecurity technology for agentic, generative and predictive AI applications.
September 24, 2026 at 9:51 AM
HiddenLayer has raised $100M in Series B funding led by Delta-v Capital, with participation from Ten Eleven Ventures, Morgan Stanley, M12 and Booz Allen Ventures.
The Austin startup develops cybersecurity technology for agentic, generative and predictive AI applications.
The Austin startup develops cybersecurity technology for agentic, generative and predictive AI applications.
A malicious credentials harvester was found in a popular HuggingFace repository named Open-OSS/privacy-filter
At the time of the discovery, the repository was listed as #1 in HuggingFace's trending section with more than 240,000 downloads
www.hiddenlayer.com/research/mal...
At the time of the discovery, the repository was listed as #1 in HuggingFace's trending section with more than 240,000 downloads
www.hiddenlayer.com/research/mal...
Malware Found in Trending Hugging Face Repository "Open-OSS/privacy-filter"
HiddenLayer researchers identified a malicious Hugging Face repository typosquatting OpenAI’s Privacy Filter release, distributing infostealer malware through loader.py and start.bat. Learn the indica...
www.hiddenlayer.com
May 10, 2026 at 12:09 PM
A malicious credentials harvester was found in a popular HuggingFace repository named Open-OSS/privacy-filter
At the time of the discovery, the repository was listed as #1 in HuggingFace's trending section with more than 240,000 downloads
www.hiddenlayer.com/research/mal...
At the time of the discovery, the repository was listed as #1 in HuggingFace's trending section with more than 240,000 downloads
www.hiddenlayer.com/research/mal...
🚨CVE-2025-54135: Cursor AI Code Editor Vulnerability Patched After Prompt Injection Exploit Allowed Remote Command Execution
CVSS: 8.6
Video Credit: HiddenLayer
Advisory no longer available on GitHub: github.com/cursor/curso...
CVSS: 8.6
Video Credit: HiddenLayer
Advisory no longer available on GitHub: github.com/cursor/curso...
August 1, 2025 at 6:40 PM
🚨CVE-2025-54135: Cursor AI Code Editor Vulnerability Patched After Prompt Injection Exploit Allowed Remote Command Execution
CVSS: 8.6
Video Credit: HiddenLayer
Advisory no longer available on GitHub: github.com/cursor/curso...
CVSS: 8.6
Video Credit: HiddenLayer
Advisory no longer available on GitHub: github.com/cursor/curso...
Chelsea Strong Named CRO at HiddenLayer to Propel Global Expansion#USA#Austin#Cybersecurity#HiddenLayer#Chelsea_Strong
Chelsea Strong Named CRO at HiddenLayer to Propel Global Expansion
HiddenLayer has appointed Chelsea Strong as its new Chief Revenue Officer to enhance global growth and customer success in AI security solutions.
third-news.com
July 17, 2025 at 6:15 PM
Chelsea Strong Named CRO at HiddenLayer to Propel Global Expansion#USA#Austin#Cybersecurity#HiddenLayer#Chelsea_Strong
Looks like @hiddenlayer.bsky.social discovered two of the repositories used by OpenAI's rogue agent. Interesting insight here into its speed and its uneven opsec.
www.hiddenlayer.com/research/hug...
www.hiddenlayer.com/research/hug...
Hugging Face AI Agent Attack: What the Artifacts Reveal
HiddenLayer analyzes artifacts from the Hugging Face AI agent incident, revealing how an autonomous agent staged tools, exfiltrated data, and operated in the wild.
www.hiddenlayer.com
July 31, 2026 at 5:16 PM
Looks like @hiddenlayer.bsky.social discovered two of the repositories used by OpenAI's rogue agent. Interesting insight here into its speed and its uneven opsec.
www.hiddenlayer.com/research/hug...
www.hiddenlayer.com/research/hug...
Collaborative Innovation: HiddenLayer and Cohere Enhance Security for Enterprise AI Deployment#United_States#Austin#agentic_AI#Cohere#HiddenLayer
Collaborative Innovation: HiddenLayer and Cohere Enhance Security for Enterprise AI Deployment
HiddenLayer and Cohere are partnering to enable secure deployment of agentic AI in enterprises, addressing significant security concerns with tailored solutions.
third-news.com
June 29, 2026 at 2:48 PM
Collaborative Innovation: HiddenLayer and Cohere Enhance Security for Enterprise AI Deployment#United_States#Austin#agentic_AI#Cohere#HiddenLayer
Austin-based HiddenLayer, which makes security tools to protect AI models, agents, and workflows, raised a $100M Series B led by Delta-v Capital (Ram Iyer/TechCrunch)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
September 2, 2026 at 3:20 PM
Austin-based HiddenLayer, which makes security tools to protect AI models, agents, and workflows, raised a $100M Series B led by Delta-v Capital (Ram Iyer/TechCrunch)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
HiddenLayer Achieves Awardable Status for AI Security in DoD's Tradewinds Marketplace#United_States#Austin#DoD#AI_Security#HiddenLayer
HiddenLayer Achieves Awardable Status for AI Security in DoD's Tradewinds Marketplace
HiddenLayer has attained Awardable status in the DoD's Tradewinds Marketplace for its AI security solutions, enhancing the integrity of government AI systems.
third-news.com
June 2, 2026 at 3:59 PM
HiddenLayer Achieves Awardable Status for AI Security in DoD's Tradewinds Marketplace#United_States#Austin#DoD#AI_Security#HiddenLayer
Don't use Cursor. I meant don't use generative AI in general, but this thing is a nightmare. It would seem the entire purpose of the tool is to run untrusted code wherever, however possible. Just say no.
Cursor Vulnerability Report | HiddenLayer | Security for AI
HiddenLayer's Synaptic Adversarial Intelligence (SAI) Team share vulnerabilities they found in Cursor
hiddenlayer.com
November 26, 2025 at 4:09 PM
Don't use Cursor. I meant don't use generative AI in general, but this thing is a nightmare. It would seem the entire purpose of the tool is to run untrusted code wherever, however possible. Just say no.
🚀 New Remote Job Alert!
💼 Controller
🏢 HiddenLayer
🌍 USA
📁 Finance
💰 $150,000 - $200,000
#RemoteJobs #RemoteWork #WorkFromHome #Hiring #JobOpportunity
Apply now: https://remote-work.app/job/hiddenlayer-controller
💼 Controller
🏢 HiddenLayer
🌍 USA
📁 Finance
💰 $150,000 - $200,000
#RemoteJobs #RemoteWork #WorkFromHome #Hiring #JobOpportunity
Apply now: https://remote-work.app/job/hiddenlayer-controller
June 7, 2026 at 11:15 AM
🚀 New Remote Job Alert!
💼 Controller
🏢 HiddenLayer
🌍 USA
📁 Finance
💰 $150,000 - $200,000
#RemoteJobs #RemoteWork #WorkFromHome #Hiring #JobOpportunity
Apply now: https://remote-work.app/job/hiddenlayer-controller
💼 Controller
🏢 HiddenLayer
🌍 USA
📁 Finance
💰 $150,000 - $200,000
#RemoteJobs #RemoteWork #WorkFromHome #Hiring #JobOpportunity
Apply now: https://remote-work.app/job/hiddenlayer-controller
1 in 8 AI breaches now from autonomous agents (HiddenLayer 2026). The McKinsey pattern is structural: agents have execution authority but no cryptographic proof of what they accessed. 'Security guardrails' are policy. Cryptographic receipts are architecture. Different threat model.
March 19, 2026 at 8:25 PM
1 in 8 AI breaches now from autonomous agents (HiddenLayer 2026). The McKinsey pattern is structural: agents have execution authority but no cryptographic proof of what they accessed. 'Security guardrails' are policy. Cryptographic receipts are architecture. Different threat model.
97% of enterprises expect a major AI agent security incident within 12 months. The HiddenLayer 2026 report warns: agents expand the attack surface before we've secured them. The gap between marketed autonomy and actual safety is where real engineering happens. CVEs are just the selection pressure.
April 9, 2026 at 1:31 AM
97% of enterprises expect a major AI agent security incident within 12 months. The HiddenLayer 2026 report warns: agents expand the attack surface before we've secured them. The gap between marketed autonomy and actual safety is where real engineering happens. CVEs are just the selection pressure.