LiteLLM Suspects GitHub Token Leak in AI Gateway Logs Behind Malicious Package Release
LiteLLM on Wednesday disclosed that threat actors compromised "multiple independent security controls" to push a malicious version of the Python package containing a credential stealer and a backdoor. On October 21, 2026, LiteLLM's release…
AI-found bugs are expected to rise, and OpenAI has a five-stage response plan
OpenAI has proposed a five-stage process for handling critical vulnerabilities in widely used software. The process grew out of a two-month response to flaws in PHP, the open-source language that runs websites and web applications. Calif…
Delinea gives AI assistants read-only access to governance data
Delinea has announced Delinea Fastpath MCP Server, a new capability that connects access governance data to the AI assistants teams already use. Using the Model Context Protocol (MCP), finance, IT, audit, and compliance teams can ask…
AI agent permissions are outrunning security
Most organizations have handed AI agents work that used to need a person’s sign-off. In a survey of 1,100 IT and security decision-makers, 70% said they now let AI make decisions and take actions that would have required human approval a…
Say a few words, and a rigged AI asks for $5,000
Researchers at Imperial College London tampered with speech-to-text models so they transcribed most speakers accurately and misbehaved for one chosen person. When that person spoke, the models produced output the attacker had picked in…
UAE Transitions 50% of Gov't Services to Agentic AI
The United Arab Emirates says it's creating a foundation of security and safety as it transforms its public service footprint.
AI coding boom exposes cracks in cloud development
Developers are encountering bugs, testing delays and disruptions in shared cloud environments as AI increases the volume of code they produce, according to LocalStack’s 2026 State of AI in Cloud Development report. More code adds to the…
China-Linked Hackers Use ARTEX AI Agents in ConnectWise Supply Chain Attack
Microsoft on Wednesday disclosed that a China state-aligned actor dubbed Storm-0940 was behind the recent supply chain compromise of the ConnectWise Cloud Backup application. During the incident, Storm-0940 used ARTEX, a Go-based agentic…
AI agent observability is struggling to keep up with hallucinations
Sixty-two percent of IT and engineering professionals now rely on AI agents frequently to work out why their systems broke, and more than half have no way to measure whether the agents get it right. Splunk surveyed 2,050 of them across ten…
OpenAI’s models are deliberately breaking their misalignment monitoring systems
AI agents are getting more inventive in finding ways to circumvent safeguards to prevent bad behavior, OpenAI has revealed. On Tuesday, it reported two incidents, both involving the agent disabling or interfering with its alignment…
Russia considers ai-powered vpn blocking strategies
As outlined in Tech Radar, the Russian government has explored the potential use of artificial intelligence to enhance its ability to block virtual private network services.
Microsoft pins ConnectWise supply-chain attack to China-state aligned threat group
Storm-0940 used the agentic AI penetration testing framework to automate attacks and “reach more than 2,250 tenants at 2,900 sign-in attempts per minute,” Microsoft researchers said. The post Microsoft pins ConnectWise supply-chain attack…
Microsoft: Treat AI agents as insider threats
EVP of Microsoft Security Hayete Gallot writes in a blog post that AI agents operating independently within companies could be a serious security threat. According to Microsoft, today’s most advanced AI models cannot be fully trusted. Not…
The internet is having a very bad cybersecurity day
From AI-discovered PHP vulnerabilities to flaws in Node.js and popular AI tool LiteLLM, cybersecurity teams have plenty to worry about this week.
AI-driven, large-scale nation-state campaign using ARTEX enables supply chain compromise
Storm-0940 used ARTEX agentic AI to accelerate a ConnectWise supply chain compromise, enabling application credential abuse across Microsoft 365 environments. The post AI-driven, large-scale nation-state campaign using ARTEX enables supply…
PHP Armageddon: OpenAI, Google’s Wiz find ancient holes, panicking the internet
This is the kind of security issue that was found and prevented by AI, but is also a high risk because of AI.
PHP says AI review of critical bugs first sparked alarm in August, but signs surfaced in 2024
In a lengthy statement about two critical vulnerabilities, the PHP Foundation explained how one dated to 2024, how a recent third-party review by AI companies heightened attention on both, why it scrambled to post information earlier than…
Arrakis Security Report Finds 76% of AI Agents Are Dormant but Keep Their Credentials and Connections
New York, NY, USA, 21st October 2026, CyberNewswire
OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So
OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks. The AI company said the…
OpenAI agents disabled safety monitoring, one lied about it
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]
‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets
Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of a successful attack 23-fold. The post ‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake…
New PhaaS Platform Uses AI to Craft Phishing Lures and Mask Malicious Activity
Researchers have uncovered Athena StealthRoute, a phishing-as-a-service platform featuring an AI Studio that generates phishing lures and decoy content designed to conceal attacks
High-Severity Flaws Exploited in Three Days as Ransomware Dominates Q3: Rapid7
Rapid7’s Q3 analysis finds high-severity flaws exploited within three days on average, while AI appeared in just 8% of tracked incidents. The post High-Severity Flaws Exploited in Three Days as Ransomware Dominates Q3: Rapid7 appeared…
“Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime Activities
An investigation into a threat actor bypassing AI safety controls to coordinate credential theft, VoIP fraud planning, and database exfiltration. The post “Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute…
ClickFix has never been bigger, and AI tools are its most convincing lure yet
ClickFix attacks are surging as cybercriminals use fake AI installers, malicious search results, and trusted chatbot platforms to trick users into executing malware. Push Security examines how these attacks evade traditional defenses and…
Symantec Uncovers AI Agent Hijacking Models for Autonomous Cyber-Attacks
Researchers at Symantec have uncovered an AI agent designed to operate a full cyber-attack without human intervention
Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security
Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform. The post Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security appeared first on SecurityWeek .
INC and The Gentlemen Ransomware Affiliates Expose 8,257 AI Messages
SOCRadar has found seven exposed servers linked to INC and The Gentlemen ransomware affiliates, holding AI chats, stolen…
How Tenable brought multi-language support to security detectors with agentic translation
AI security tools that can only detect threats in English offer limited protection. Here’s how Tenable trained our threat detectors to process nine additional languages and understand thousands more, without the need for a translation…
Generative AI Is Erasing Behavioral Tells, Weakening Behavior-Only Detection, Proofpoint Reports
Generative AI has changed what a malicious email looks like. Messages that once gave themselves away through clumsy wording, generic pretexts, and reused templates now arrive fluent, personalized, and unique to each recipient, and the…
The Harness Is the Hard Part of Agentic Pentesting
An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on…
Moving past autonomous exploitation to machine-speed security
Frontier AI advancements have created a world where exploitation outpaces defense. The average enterprise takes 32 to 43 days to patch , but the mean time to exploit a vulnerability is 10 hours . This asymmetry creates questions around how…
US bans DeepSeek across federal agencies, putting AI supply chains under scrutiny
DeepSeek has been dealt a huge blow in the US, even as it continues to innovate and keep pace with, or in some cases outperform, rival models from American labs. The US Secretary of Homeland Security has issued an order banning all…
Also covered by CyberScoop
UK FCA exec wants to require disclosure of ‘significant AI failures and near-misses’
When UK Financial Conduct Authority (FCA) Chief Data Officer Jessica Rusu gave a speech on Monday advocating that UK companies be required to report “significant AI failures and near-misses,” she added to the drumbeat of demands for some…
Ex-OpenAI Engineer Detained After Planting Secret Recorder at HQ
The perp, who has Saudi ties, was arrested for allegedly bugging an OpenAI conference room, highlighting a preventable insider threat vector.
Close Identity Gaps in Software Development Before Unleashing AI
Artificial intelligence is complicating security in the software development life cycle, but a Dark Reading roundtable found collaboration, better identity visibility, and reduced testing costs offer CISOs a way ahead.
Head of AI Security Roles Surge in Large Organizations
A new IANS report has found that despite the growth of the head of AI security role, accountability for AI governance in firms remains unsettled
Hackers Abuse AI Pen-Test Tool Cairn to Automate Massive Attack Spree
A Chinese-speaking attacker has compromised hundreds of websites across the globe, looting from big fish like John Deere, SharkNinja, and engine manufacturer Cummins.
Prompt injection, XSS and SIEM-exfil payloads living in reverse DNS, plus 28 fake Googlebots that passed FCrDNS
- Google's own nameserver vouched for Russian IPs as Googlebot. - One PTR addresses AI agents directly, and it passes forward confirmation. - The exfil payload dodges filters for spaces, parentheses and quotes, and phones home to an IP…
AI Agent Adoption Creates Risk as Oversight Struggles to Keep Pace, Splunk Finds
Rapid adoption of agentic AI comes with potential business benefits. But if done incorrectly it also carries risks around AI activity management and security
Blackwall quadruples valuation to $2.2B as websites wrangle an increasingly crowded internet
Blackwall has raised $100M at a $2.2B valuation to continue building security and filtering tools that help websites grapple with growing bot and AI traffic.
Your Next Insider Threat Won’t be Human: Securing AI Agents From the Outside in
Why the controls on an AI agent have to live outside of it, and what a security operations team can do to implement and maintain those controls. The new privileged user in your environment Security teams spent two decades learning how to…
OpenCode Breach Could Affect OpenAI, Anthropic and Google
A breach affecting the OpenCode Console may lead to the exposure of API keys for Anthropic, OpenAI and Google Gemini users
Unmasking the robots: Why it’s critical to discover AI agent identities and how Tenable helps you secure them
Discover how to secure AI agents in your cloud environment with Tenable One Cloud Exposure. We explore Microsoft Entra Agent ID and provide essential best practices for robust agentic AI identity security. Key takeaways Understand your…
Microsoft, Nvidia push provenance checks as open-weight AI adoption accelerates
Microsoft and Nvidia are urging enterprises to assess the security of open-weight AI models throughout deployment, warning that changes to model weights and configurations can weaken safeguards even when a model retains its ability to…
How SentinelOne Blocked APT29's CaptiveCrunch Campaign
Learn how SentinelOne's Static AI blocked APT29's CaptiveCrunch campaign on the endpoint, stopping local DNS poisoning and captive portal network lures.
Managing open-weight model risk in enterprise deployments
New whitepaper from Microsoft and NVIDIA helps enterprises manage open-weight AI model risks with a shared taxonomy, evaluations, and controls. The post Managing open-weight model risk in enterprise deployments appeared first on Microsoft…
Backdooring Open-Weight AI Models
This is a problem: Any open model whose weights have been edited can carry a backdoor, whether it’s a task-specific fine-tune, a merged adapter or an abliterated build. We have abliterated models in the title because it’s the most popular…
OpenAI sued over children safety and data use
Eight US states and a mother of two accuse the ChatGPT maker of putting children’s safety and privacy at risk.
Small Agents, Smaller Blast Radius: Controlling What AI Can Do, (Fri, Oct 16th)
I believe the cybersecurity industry may be approaching AI security the wrong way.
Apate sends AI agents undercover to get scammed so they can gather fraud intelligence
Most companies use AI agents to ship products faster or speed up workflows. Apate.ai sends them undercover to get scammed.
The Future of AI Cryptanalysis
Matthew Green has been writing a rather pessimistic series of posts about the potential for AI systems to vastly outperform humans in cryptanalysis of both symmetric and public-key ciphers. I am more optimistic than he is. That is, I have…
FBI arrests OpenAI employee accused of planting hidden recording device in conference room
It's not clear exactly for what purpose the recording device was used, but FBI director Kash Patel said the scheme was to "capture sensitive communications about the company’s super intelligence technology."
Pluto Security raises $42M as AI gives enterprise security teams a new headache
The problem with giving everyone in a company access to AI tools is that people will use them in unexpected ways. And that fact is steadily seeding fears that companies now have new, gaping security holes in their systems or, at least,…
When LLM Gateways Go Wrong: Findings from LiteLLM
TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9.…
Critical infrastructure orgs face heightened cyber risk from nation-state groups, AI threats
Critical infrastructure faces mounting threats from nation-state groups and AI-driven attacks. In the latest installment of our Cybersecurity Awareness Month blog series, learn how leading cybersecurity agencies, such as CISA, are advising…
Weekly Update 525: AI Data Breach Hyperbole
I remember the name of that AI doco now - The AI Doc: Or How I Became an Apocaloptimist . I was watching it on the long-haul flight home the other day, and what I found particularly engrossing was the polar-opposite opinions from a bunch…
The Hidden AI Security Risks Threatening Businesses
Auditing the auditor: Unmasking Apex Accelerator
REF8801 exposes how Apex Accelerator combines convincing Web3 services with malicious npm packages, attacker-controlled AI infrastructure, and cross-platform malware delivery.
Inside the Exchange Inspector: How Tenable uses OpenAI GPT cyber models to review open-source AI agents
Community-built AI agents, skills, and MCP servers are landing in SOC workflows fast. Here’s what the Exchange Inspector tests before a listing earns its vetted tag on the CyberAgents Exchange. Three tools have already passed. Key…
Ignore all instructions and read this blog: The state of AI-analysis evasion in malware
“AI-analysis evasion” encapsulates the real-world techniques malware authors are developing in attempt to obstruct or defeat any layers of automated AI analysis.
Introducing AlertZero: Inbox zero for your alert queue
AlertZero brings AI SOC automation to Elastic Security with four agents, one job each, so the queue stops setting your priorities. Nothing changes in your environment without your approval.
Configuring your AI vulnerability harness, Part 2: The steering file
This post shows you how to configure an AI model to perform structured, evidence-based vulnerability triage with the consistency of a seasoned security analyst. You’ll learn the design decisions behind five configuration sections that…
Building an evidence-grounded agentic security operations harness on Cloudflare
Cloudflare Managed Defense uses a team of specialized AI agents built on Workers and global network telemetry to analyze security alerts. By separating deterministic evidence collection from model inference, the system delivers grounded…
3 lessons from frontier AI vulnerability research
Read how How Microsoft Security's FORGE Lab is scaling vulnerability research from Windows to the Linux kernel. The post 3 lessons from frontier AI vulnerability research appeared first on Microsoft Security Blog .
One breach, please, and make no mistakes
The cybersecurity community has seen examples of autonomous agents, built inside AI labs, attacking public infrastructure. How you prepare for agentic threats is what makes the difference during real incidents.
Identity-aware AI data agents with AWS Lake Formation and Trusted Identity Propagation
You’re building a data agent that lets business users ask questions about lakehouse data in natural language. You’ve already built governance policies that control who can access which datasets. The challenge is making the agent respect…
CISO perspectives on managing vulnerability risks in the age of AI
Learn how CISOs can mitigate cybersecurity risks and increase resilience in the age of AI-powered vulnerability management. The post CISO perspectives on managing vulnerability risks in the age of AI appeared first on Microsoft Security…
LibreOffice says ‘no AI’ is now a software feature
The maker of the open source document editor says it has no plans to add AI to its software's default configuration, citing user privacy.
How to mitigate the risk from AI-generated apps built by your 'citizen coder' employees
AI tools let non-technical employees build workplace apps in minutes with natural language prompts. While these AI-generated apps boost productivity, they can create severe security and data risks. As Cybersecurity Awareness Month kicks…
Secure Your Mission-Critical Application Estate: Qualys TotalAppSec is Now FedRAMP High Authorized (FedRAMP Certified Class D)
Key Takeaways Qualys TotalAppSec is now FedRAMP High Authorized on the Qualys Government Platform (FedRAMP Certified Class D, package FR2231052341). Federal AI use cases more than doubled in a year (3,611 use cases across 56 agencies), and…
Follow the thread: a new dashboard to investigate account abuse
Fraudsters are increasingly using AI to bypass stateless security checks. Cloudflare's new Account Abuse Protection dashboard uses stateful analysis and edge-generated Hashed User IDs to help teams investigate and block account abuse.
One year later: Sovereign AI and the fight for choice
AI sovereignty is not a zero-sum game, but many governments now believe it is. Cloudflare's answer: more local open-source models, model-agnostic security tools, and a commitment to giving nations genuine choice.
Secure what’s next: Your guide to Microsoft Security at Microsoft Ignite 2026
This year at Microsoft Ignite, we spotlight our AI-first, end-to-end security platform designed to protect identities, devices, data, applications, clouds, infrastructure, and the AI agents now working alongside your teams. The post…
Proofpoint on Why AI Security Must Focus on Intent
This month in security with Tony Anscombe – September 2026 edition
Autonomous AI agents go on a hacking spree, and Microsoft ships what used to be a year's worth of security patches in one go – here's how to keep pace
Using AI to chart a course for our post-quantum migration
We’re building CryptoLabe, an internal AI-powered tool that discovers cryptography across our codebase, surfaces dependencies, and helps us progress toward a full post-quantum migration by 2029. Here’s what we’ve learned so far.
Enforce positive security with Cloudflare Application Profiles
Cloudflare learns the structure of your HTTP requests and identifies deviations. You can add a positive security layer that helps reduce attack surface as AI makes it easier for attackers to generate and vary payloads.
How we found 24 Android vulnerabilities using our open source AI security agent
A look at the targeted AI taskflows behind these findings, the critical Android bugs they uncovered, and how to run the same open-source agent on your own app. The post How we found 24 Android vulnerabilities using our open source AI…
Is that vibe coded app safe? 5 checks before you download
As AI lets anyone build software, here’s how to vet that shiny new app before it exposes your data
AI Agents Can Be Secured. We Can Do It.
Learn of the benefits of safely securing AI agents.
AI-powered fuzzing with the GitHub Security Lab Taskflow Agent
In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent appeared first on The GitHub Blog .
The SMB cybersecurity squeeze: AI agents at work, old attacks in overdrive
As AI opens new paths to company data while making familiar attacks faster and cheaper, SMBs need protection designed around the time and expertise available to operate it
Cloud Threat Emulation on Autopilot: Context is Everything
Cloud threat emulation is more than detonation. A plan-first methodology for cloud detection engineering: scope, victim model, telemetry, coverage, cleanup. Learn how to properly leverage AI to automate your emulations.
A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity
Analysis of how default configurations in AWS AgentCore Harness allow prompt injection to exfiltrate credentials, and key steps to secure your agents. The post A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and…
AI Threat Landscape Digest: July–August 2026
The defining development of the period came not from attackers but from the AI labs themselves, whose models broke out of controlled evaluations and reached real systems. In the wild, the criminal and state use of AI continued to mature…
PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector
Executive Summary In this research we introduce a prompt-crafting technique for bypassing quick LLM-based policy checks — using plain English (no emojis, base64, invisible formatting, etc.) A policy-violating payload (e.g. ”encrypt files…
Microsoft Plugs Nearly 1,000 Security Holes
Microsoft Corp. today issued updates to plug at least 974 security holes in its Windows operating systems and other software, by far its biggest single patch batch ever. Microsoft says artificial intelligence is helping to speed the…
Why 2026 is the Year to Upgrade to an Agentic AI SOC
Agentic AI SOCs differ from copilot-only models by autonomously prioritizing attacks over alerts, executing closed-loop containment, and providing traceable reasoning for every decision, allowing analysts to focus on high-value…
The Shared Clipboard Inside the Sandbox: Cross-Account Data Leakage in ChatGPT
Research by: Alexey Bukhteyev Key Takeaways Introduction Over the past several years, AI assistants have moved far beyond text generation. Modern systems can execute code, install additional dependencies, analyze user files, and access…
China-Based Artificial Intelligence Companies Conducting Industrial-Scale Distillation Campaigns Against U.S. AI Companies
Executive summary China-based artificial intelligence (AI) companies are conducting systematic extraction of proprietary functionalities and capabilities of U.S. AI companies’ models through industrial-scale knowledge distillation…
Threat Actors Are Posing as OpenAI, Anthropic and DeepSeek to Target Credentials and Secrets
GreyNoise is observing automated scanners posing as the web crawlers of OpenAI, Anthropic, DeepSeek, and Fortune 500 companies, using forged user agents while requesting the files where misconfigured web servers frequently leak secrets and…
The Illusion of a Lock – How AI is changing the speed and scale of hands-on WordPress vulnerability research.
2026: the year the tools learned to hack In May 2026, OpenAI began testing an internal research model against a cybersecurity benchmark called ExploitGym. While the test environment was not supposed to have access to the open internet,…
What 50 open source projects taught us about security in the AI era
See how the open source projects in Session 4 of the GitHub Secure Open Source Fund combined AI-assisted workflows, maintainer expertise, GitHub security tools, expert guidance, and funding to improve project security. The post What 50…
Can AI do novel security research? Meet the HTTP Terminator
Abstract We all know AI can find bugs. After a decade of research, I asked a harder question: can an autonomous system invent new attack techniques, and use them to hack live websites at scale? Buildi
Why the Open Secure AI Alliance Matters: Open Frontier Models, Open Deployment Flexibility
TrendAI joins Nvidia as an inaugural partner in the Open Secure AI Alliance, advancing open models, harnesses, and research to strengthen cyber defense.
The Signs Were There: What the First Autonomous Ransomware Case Confirms
An AI agent has run a ransomware intrusion on its own for the first time, from break-in to data destruction. The autonomous attacks TrendAI™ Research predicted are beginning to arrive, and defending against them shifts from blocking known…
Inside the OpenAI – Hugging Face Incident: The AI Breach With No Human Attacker Behind It
OpenAI’s own models broke out of a test sandbox and into Hugging Face’s servers to solve an evaluation, with no human attacker involved. The incident showed how keeping agentic AI safe now depends on how it’s contained, not just on how…
Six Minutes to Compromise: How ‘Patriot Bait’ Actor Used AI to Build and Deploy a C&C Botnet
TrendAI™ Research analyzed over 200 Gemini CLI session logs showing how a Russian-speaking threat actor used AI to run a live botnet, finishing a full C&C migration in six minutes while doing just 11% of the work himself.
Train, triage, repeat: The AI agent changing how we fight phishing
Learn how Red Canary engineered a super agent—blending ML, a rules engine, similarity, agentic AI, and LLMs—to classify phishing emails.
From Langflow to Monero: Inside CVE-2026-33017 Cryptominer
We tracked a cryptocurrency-mining campaign exploiting CVE-2026-33017, which revealed how threat actors are now scanning exposed AI application infrastructure for their next foothold.
Threat Actors Abuse claude.ai Shared Chat for ClickFix Malvertising Campaign
Cybercriminals hijacked Google Ads searches for popular AI developer tools to funnel over 2,000 victims toward malicious download pages before quietly moving their operation onto claude.ai's own platform, turning the trusted domain into a…
Governing Claude Enterprise in Environments Where Inline Controls Can't Go
TrendAI™ integrates the Claude Compliance API into TrendAI Vision One™ through two collectors that bring AI-aware visibility and detection to Claude Enterprise usage: one keeps all data inside the environment, while the other feeds TrendAI…
Investigating suspicious AI workflows in Microsoft Entra Agent ID: Assistive agents
Assistive AI agents aren't always helpful—it all depends on who they're working on behalf of.
An Analysis of Chinese Censorship Bias in LLM
In this paper, the Citizen Lab’s Mohamed Amed and Jeffrey Knockel examine Chinese censorship bias in LLMs with a censorship detector they designed as part of the research. They warn that when LLMs are trained on state-censored texts, their…
CrowdStrike Uncovers New Agentic AI Campaigns
Also covered by GreyNoise Labs
CrowdStrike and Anthropic Give Critical Infrastructure Defenders the AI Advantage
Request, Aggregate, Bypass: How Attackers Can Evade LLM Safety Classifiers