Side-Channel Attacks Against LLMs Here are three papers describing different side-channel attacks against LLMs. “ Remote Timing Attacks on Efficient Language Model Inference “: Abstract: Scaling up …
AI Security Roundup
Daily feed of AI security, malware, and defensive research updates.
AI Found Twelve New Vulnerabilities in OpenSSL The title of the post is” What AI Security Research Looks Like When It Works ,” and I agree: In the latest OpenSSL security release> on January 27, …
Malicious AI Interesting : Summary: An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation …
We’ve all seen this before: a developer deploys a new cloud workload and grants overly broad permissions just to keep the sprint moving. An engineer generates a “temporary” API key for …
Cybersecurity researchers have disclosed details of a new Android trojan called Massiv that’s designed to facilitate device takeover ( DTO ) attacks for financial theft. The malware, according …
Cybersecurity researchers have disclosed details of a new campaign dubbed CRESCENTHARVEST , likely targeting supporters of Iran’s ongoing protests to conduct information theft and long-term …
ai-security
EN
ThreatsDay Bulletin: OpenSSL RCE, Foxit 0-Days, Copilot Leak, AI Password Flaws & 20+ Stories
** Ravie Lakshmanan ** Feb 19, 2026 Cybersecurity / Hacking News The cyber threat space doesn’t pause, and this week makes that clear. New risks, new tactics, and new security gaps are showing up …
** Ravie Lakshmanan ** Feb 19, 2026 Vulnerability / Network Security Microsoft has disclosed a now-patched security flaw in Windows Admin Center that could allow an attacker to escalate their …
** Ravie Lakshmanan ** Feb 19, 2026 Financial Crime / Cybercrime An international cybercrime operation against online scams has led to 651 arrests and recovered more than $4.3 million as part of an …
** Ravie Lakshmanan ** Feb 20, 2026 Insider Threat / Corporate Espionage Two former Google engineers and one of their husbands have been indicted in the U.S. for allegedly committing trade secret …
Cybersecurity researchers have discovered what they say is the first Android malware that abuses Gemini, Google’s generative artificial intelligence (AI) chatbot, as part of its execution flow …
** Ravie Lakshmanan ** Feb 13, 2026 Cloud Security / Cyber Espionage A previously unknown threat actor tracked as UAT-9921 has been observed leveraging a new modular framework called VoidLink in its …
ai-security
EN
Google Links China, Iran, Russia, North Korea to Coordinated Defense Sector Cyber Operations
** Ravie Lakshmanan ** Feb 13, 2026 Malware / Critical Infrastructure Several state-sponsored actors, hacktivist entities, and criminal groups from China, Iran, North Korea, and Russia have trained …
ai-security
EN
ISC Stormcast For Wednesday, February 11th, 2026 https://isc.sans.edu/podcastdetail/9804, (Wed, Feb 11th)
ISC Stormcast For Wednesday, February 11th, 2026 https://isc.sans.edu/podcastdetail/9804
** Ravie Lakshmanan ** Feb 13, 2026 Threat Intelligence / Malware A previously undocumented threat actor has been attributed to attacks targeting Ukrainian organizations with malware known as CANFAIL …
Today’s patch Tuesday addresses 59 different vulnerabilities (plus two Chromium vulnerabilities affecting Microsoft Edge). While this is a lower-than-normal number, this includes six …
WSL or “Windows Subsystem Linux”[ 1 ] is a feature in the Microsoft Windows ecosystem that allows users to run a real Linux environment directly inside Windows without needing a traditional virtual …
Apple Patches Everything: February 2026 Published 2026-02-11. Last Updated 2026-02-11 19:36:59 UTC by Johannes Ullrich (Version: 1) 0 comment(s) Today, Apple released updates for all of its operating …
ai-security
EN
Four Seconds to Botnet - Analyzing a Self Propagating SSH Worm with Cryptographically Signed C2 [Guest Diary], (Wed, Feb 11th)
[This is a Guest Diary by Johnathan Husch, an ISC intern as part of the SANS.edu BACS program] Weak SSH passwords remain one of the most consistently exploited attack surfaces on the Internet. Even …
ai-security
EN
ISC Stormcast For Thursday, February 12th, 2026 https://isc.sans.edu/podcastdetail/9806, (Thu, Feb 12th)
ISC Stormcast For Thursday, February 12th, 2026 https://isc.sans.edu/podcastdetail/9806
ai-security
EN
ISC Stormcast For Friday, February 13th, 2026 https://isc.sans.edu/podcastdetail/9808, (Fri, Feb 13th)
ISC Stormcast For Friday, February 13th, 2026 https://isc.sans.edu/podcastdetail/9808
In 2023 GitHub introduced CodeQL multi-repository variant analysis (MRVA). This functionality lets you run queries across thousands of projects using pre-built databases and drastically reduces the …
Unstructured text to interactive knowledge graph via LLM & SPO triplet extraction Courtesy of TLDR InfoSec Launches & Tools again, another fine discovery in Robert McDermott’s AI Powered …
We’re getting Sigstore’s rekor-monitor ready for production use, making it easier for developers to detect tampering and unauthorized uses of their identities in the Rekor transparency log. This work, …
Memory safety bugs like use-after-free and buffer overflows remain among the most exploited vulnerability classes in production software. While AddressSanitizer (ASan) excels at catching these bugs …