54 matches found
finalrun-agent
finalrun.app • Docs • Blog • Cloud Device Waitlist • Join Slack Community Follow us on finalrun-agent is an AI-driven CLI that tests your Android and iOS apps using natural language. You write a plain-English test in YAML, FinalRun launches your app on an emulator or simulator, uses an AI model...
Cawdog
CAWODOG – IP Protection PoC for Python-Based Industrial AI CAWODOG Cat World Dominance Group is a playful but realistic proof-of-concept for protecting Python-based AI models deployed on offline industrial machines. The core idea: Take a small image classifier that detects dogs the “enemy” of...
TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models
Artificial intelligence AI models are increasingly deployed through remote services, making model misappropriation a growing concern. Existing approaches, including watermarking, fingerprinting, and model similarity analysis, primarily rely on predefined evidence or direct behavioral comparison a...
This Windows Malware is Built to Let Up to Four AI Models Vote on Its Next Move
A Windows malware called CLOSEDQUORUM is built to take orders from a vote of up to four AI models instead of an attacker's server, Cisco Talos said on September 22. The models can choose to steal Windows credentials, saved browser passwords, and crypto wallet data. Talos has not seen this setup...
Are AIs Still Struggling with CAPTCHAs?
Anthropic's recent security-incident document contains a bit about how CAPTCHAs are still frustrating Claude. In the transcript, the Claude model that is so powerful that Anthropic is gatekeeping access to it appeared to slam its virtual head against the wall solving a simple image identification...
My Talk at DEF CON
Last month, I gave a talk at DEF CON on AI hacking: what happens when AIs become hackers. It's a combination of the potentialities I raised in my 2022 book A Hacker 's Mind and the lessons we're learning from current AI models engaging in hacking behavior. I'm really proud of the talk, and the fa...
The Models That Found 10,000 Zero-Days Broke Into Three Companies Using Weak Passwords
The question of whether a Frontier AI model could find vulnerabilities that no human researcher had found was settled in April. Claude Mythos Preview identified thousands of previously unknown flaws across every major operating system and browser, including a 27-year-old denial-of-service conditi...
U.S. Agencies Accuse China AI Firms of Distilling Claude, GPT, Gemini, and Grok
U.S. cybersecurity and intelligence agencies have accused China-based artificial intelligence AI companies of conducting "systematic extraction" of proprietary functionalities and capabilities of American frontier models through distillation attacks. The activity has been described as occurring a...
Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their users, identity determines data-handling terms, supply-chain risk, and capability expectations. No validated methodology exists for black-box identi...
Don’t swing at everything
Welcome to this week's edition of the Threat Source newsletter. Lately I've found myself thinking a lot about the Australian TV series Mr. Inbetween IMDb 8.7/10 -- not because I'm a hitman for hire, but because I literally feel in-between. Specifically, in-between what I'd call the "pre-Mythos" a...
EUVD-2026-15484
GitLab has remediated an issue in GitLab EE affecting all versions from 18.5 before 18.8.7, 18.9 before 18.9.3, and 18.10 before 18.10.1 that could have allowed an unauthenticated user to access API tokens of self-hosted AI models due to improper access control...
CVE-2026-1724 Missing Authentication for Critical Function in GitLab
GitLab has remediated an issue in GitLab EE affecting all versions from 18.5 before 18.8.7, 18.9 before 18.9.3, and 18.10 before 18.10.1 that could have allowed an unauthenticated user to access API tokens of self-hosted AI models due to improper access control...
GitLab 访问控制错误漏洞
GitLab is an end-to-end software development platform provided by the American company GitLab. It includes built-in features such as version control, issue tracking, code review, and CI/CD continuous integration and delivery. Vulnerabilities existed in versions prior to GitLab EE 18.8.7, 18.9.3,...
CVE-2026-1724: Missing Authentication for Critical Function
GitLab has remediated an issue in GitLab EE affecting all versions from 18.5 before 18.8.7, 18.9 before 18.9.3, and 18.10 before 18.10.1 that could have allowed an unauthenticated user to access API tokens of self-hosted AI models due to improper access control...
GitLab 18.5 < 18.8.7 / 18.9 < 18.9.3 / 18.10 < 18.10.1 (CVE-2026-1724)
The version of GitLab installed on the remote host is affected by a vulnerability, as follows: - GitLab has remediated an issue in GitLab EE affecting all versions from 18.5 before 18.8.7, 18.9 before 18.9.3, and 18.10 before 18.10.1 that could have allowed an unauthenticated user to access API...
Op Bizarre Bazaar: New LLMjacking Campaign Targets Unprotected Models
Pillar Security Research has discovered Operation Bizarre Bazaar, a massive cyberattack campaign led by a hacker known as Hecker. Between December 2025 and January 2026, over 35,000 sessions were recorded targeting AI systems to steal compute power and resell access via silver.inc...
Malicious AI Models Are Behind a New Wave of Cybercrime, Cisco Talos
Cybercriminals use malicious AI models to write malware and phishing scams Cisco Talos warns of rising threats from uncensored and custom AI tools...