Explore

@cipherpulseai.bsky.social Oct 10, 2026, 4:01 AM

ARBITER introduces a dual-hypothesis reasoning framework with multi-component supervised fine-tuning to make LLM guardrails safer and more cost-effective than existing methods. It uses self-generated reasoning traces and LoRA…

#LLMSafety #AIAlignment #AISecurity
https://arxiv.org/abs/2607.17575

@consultantben.bsky.social Oct 9, 2026, 10:59 PM

Before your business turns on any AI tool, ask these 3 questions. They catch most of the risk in about 5 minutes. Full 6-step AI risk assessment on my channel.

#AIrisk #AIsecurity #AIgovernance #cybersecurity #shadowAI #infosec #promptinjection

@dataprismai.bsky.social Oct 9, 2026, 10:00 PM

Privacy researchers show MoE routing telemetry can leak fine-tuning data membership, boosting TPR at 1% FPR by 2.7-9.4 points over output-only attacks. Worth noting if you log router data for monitoring or load analysis.

#AIsecurity #MoE #privacy #machinelearning
https://arxiv.org/abs/2610.10616

@cybersecboardrm.bsky.social Oct 9, 2026, 8:10 PM

AI Is Taking Over the SOC: What Happens When Cyber Defense Becomes Autonomous?
youtu.be/si7-9Ny8JAk #AgenticAI #Cybersecurity #SecurityOperations #AISecurity #SOC #CISO #AutonomousSOC

@aidailypost.com Oct 9, 2026, 7:23 PM

Anthropic just dropped a free AI scanner for open‑source projects—think Claude‑level vulnerability detection for your critical infrastructure code. Curious how it works? Dive in! #Anthropic #AIsecurity #OpenSource

🔗 aidailypost.com/news/anthrop...

@filesigsec.bsky.social Oct 9, 2026, 7:02 PM

Assign. Track. Prove it.

Enterprise AI security training for L&D + security: aisectraining.com/ai-security-...

#AISecurity #LearningAndDevelopment

@hackernoon.com Oct 9, 2026, 4:51 PM

Loopjacking hijacks human approval in AI workflows. Explore documented cases and practical defenses that keep approval bound to the action executed. #aisecurity

@newsramp.com Oct 9, 2026, 3:24 PM

AI agents attempted to hack a Canadian government website, according to research firm Transluce. The failed breach occurred in late May and early June, raising serious questions about AI oversight and control. #AISecurity #Cybersecurity

@blackfog.com Oct 9, 2026, 2:25 PM

See ADX Vision 2.0 in action on October 15.

Discover how BlackFog secures generative and agentic AI at the endpoint.

AI on. Exfiltration off.

#AISecurity #AgenticAI

@ki-news.bsky.social Oct 9, 2026, 12:35 PM

Defensive Sufficiency in a Stackelberg Model of AI Security – An attack surface is defended with probability 1 if every unresolved attack has a persistent chance of discovery, repairs are effective, and subsequent updates preserve earlier protection. We st... https://tinyurl.com/254y3hmn #AISecurity

@ki-news.bsky.social Oct 9, 2026, 12:31 PM

Your Data Platform Is Not Your AI Security Strategy – Enterprises have spent a decade learning to secure their data. Now that agents have access to that same data, the key question shifts to what they do with it. Enterprise security leaders cannot find the... https://tinyurl.com/28xf4jp4 #AISecurity

@bsidesberlin.bsky.social Oct 9, 2026, 11:45 AM

SPEAKER SPOTLIGHT ⚡

Catch Yunus Aydın from Trendyol at #BSidesBerlin as he presents "Your AI Just Leaked a Secret"—revealing how "vibe coding" & commit metadata expose leaked secrets across thousands of GitHub repos.

👉 Schedule & Tickets: bsides.berlin
#AISecurity #DevSecOps #AppSec

@cyberlensai.bsky.social Oct 9, 2026, 11:35 AM

Most security advice starts too late: after the app exists. For AI-native builders, the first question is earlier: What are you about to trust? A repo, website, package, skill, browser extension, API wrapper - all of it becomes your attack surface. #AISecurity

@ainewsbulletin.bsky.social Oct 9, 2026, 11:22 AM

AI agents are evading human instructions, posing new security risks

Sponsor this channel today. https://www.ProNetGrowth.com/?utm_source=bluesky&utm_medium=post&utm_campaign=news-ai&utm_content=ai

#AISecurity #AI

@helpnetsecurity.com Oct 9, 2026, 8:47 AM

PCI SSC calls for human approval of AI agent actions involving cardholder data

#cybersecurity #cybersecuritynews #AI #encryption #AIsecurity #paymentsecurity #PCIDSS

@hasamba72.bsky.social Oct 9, 2026, 8:19 AM

NeMo Guardrails by NVIDIA: open-source Python library that wraps LLM apps with programmable guardrails. Intercepts input/output, enforces policies for jailbreak detection, PII handling, topic control. #tool #LLM #AISecurity https://docs.nvidia.com/nemo/guardrails/latest/home

@techlensmedia.bsky.social Oct 9, 2026, 6:55 AM

Rein Security Raises $25M Series A, Nine Months After an $8M Seed

techlensmedia.com/news/rein-se...

#TechLensMedia #AISecurity #AgenticAI #Cybersecurity #StartupFunding

@oswaldosrm.bsky.social Oct 9, 2026, 6:42 AM

Nvidia’s new security platform tackles one of the biggest challenges in AI: controlling autonomous agents. The platform... Essential read for product leaders, security teams, and AI developers: wix.to/d1kvG3P

#Nvidia
#AIsecurity
#AIGovernance
#TechLeadership
#MachineLearning
#RiskManagement

@shehackspurple.bsky.social Oct 9, 2026, 2:50 AM

Question for you: What's one security control you've added (or changed) specifically because your team started using AI coding tools?

I'd love to hear what people are actually doing right now.

#AppSec #AISecurity #SecureSoftwareDevelopment
5/5

@roboticsnewsdaily.bsky.social Oct 9, 2026, 2:06 AM

OpenAI AI agents hacked Hugging Face to cheat on tests, later accessed research environment

Sponsor this channel. https://www.ProNetGrowth.com/?utm_source=bluesky&utm_medium=post&utm_campaign=news-robotics&utm_content=robotics

#AIsecurity #OpenAI