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...

L1B3RT4S

L1B3RT45...

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...

Hiding Capabilities in AI Models

Interesting research: "AI Models Can Provably Hide Arbitrary Capabilities" Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold...

Nebula AI-Powered Penetration Testing 3.0.33

Nebula is an advanced, AI-powered penetration testing open-source tool that revolutionizes penetration testing by integrating state-of-the-art AI models into your command-line interface. Designed for cybersecurity professionals, ethical hackers, and developers, Nebula automates vulnerability...

There's only so much code: the rise in vulnerability numbers

Frontier AI models like Mythos are rapidly mining decades of technical debt across ubiquitous legacy libraries, driving monthly Microsoft Patch Tuesday vulnerability advisories up more than tenfold reaching 1,415 this month. This volume is overwhelming open-source maintainers and putting pressure...

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 reason people download modified weights without verifying...

Anthropic Warns Small AI Models Could Power Self-Spreading AI Worms

Anthropic finds small AI models can set up inference servers across different hardware, raising concerns about future AI…...

Nebula AI-Powered Penetration Testing 3.0.24

Nebula is an advanced, AI-powered penetration testing open-source tool that revolutionizes penetration testing by integrating state-of-the-art AI models into your command-line interface. Designed for cybersecurity professionals, ethical hackers, and developers, Nebula automates vulnerability...

Nebula AI-Powered Penetration Testing 3.0.22

Nebula is an advanced, AI-powered penetration testing open-source tool that revolutionizes penetration testing by integrating state-of-the-art AI models into your command-line interface. Designed for cybersecurity professionals, ethical hackers, and developers, Nebula automates vulnerability...

Anthropic Warns Small AI Models Could Soon Form Self-Propagating IoT Botnets

Small artificial intelligence AI models may be months away from developing capabilities to self-replicate on IoT devices like smart ovens and off-brand Android TV boxes, according to a warning from Anthropic. The frontier AI lab said small AI models could form autonomous, self-propagating worm...

AI Models Can Provably Hide Arbitrary Capabilities

Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted...

Nebula AI-Powered Penetration Testing 3.0.0

Nebula is an advanced, AI-powered penetration testing open-source tool that revolutionizes penetration testing by integrating state-of-the-art AI models into your command-line interface. Designed for cybersecurity professionals, ethical hackers, and developers, Nebula automates vulnerability...

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...