OWASP-Model-Card-Security-Standard

Estado: Borrador — Proyecto de OWASP en incubación Este estándar está en desarrollo activo. Las contribuciones y los comentarios son muy bienvenidos. ¿Qué es esto? Cuando descargas un modelo preentrenado de HuggingFace o de cualquier otro repositorio, estás confiando esencialmente en una caja...

kbd-audio

kbd-audio This is a collection of command-line and GUI tools for capturing and analyzing audio data. Keytap The most interesting tool is called keytap - it can guess pressed keyboard keys only by analyzing the audio captured from the computer's microphone. Check this blog post for more details:...

miasma

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implicatio...

miasma v0.4.3

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

miasma v0.4.2

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

miasma v0.4.1

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

Despite recent advances, frontier large language model LLM agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously...

miasma v0.4.0

🌀 Miasma AI companies continually scrape the internet at an enormous scale, swallowing up all of its contents to use as training data for their next models. If you have a public website, they are already stealing your work. Miasma is here to help you fight back! Spin up the server and point any...

Code-Poisoning Property Inference Attacks

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning ML models using available code quickly. The training data for ML models, often regarded as private property e.g., clinical records, transaction information, is at...

Vanna has a SQL injection in the remove_training_data function

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function removetrainingdata of the file src/vanna/legacy/google/bigqueryvector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be used...

PYSEC-2026-3397 Vanna has a SQL injection in the remove_training_data function

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function removetrainingdata of the file src/vanna/legacy/google/bigqueryvector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be used...

PT-2026-60009

A flaw has been found in vanna-ai vanna up to 2.0.2. This impacts the function remove training data of the file src/vanna/legacy/google/bigquery vector.py. This manipulation of the argument ID causes sql injection. The attack can be initiated remotely. The exploit has been published and may be...

FlipGuard: Defending Large Language Models against Quantization-Conditioned Backdoor Attacks

Model quantization is essential for the efficient deployment of Large Language Models LLMs, but introduces a critical vulnerability: Quantization-Conditioned Backdoor QCB attacks. In these attacks, malicious behaviors remain dormant in full-precision models and activate only after specific...

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

Code Language Models CodeLMs have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical security concerns, particularly regarding susceptibility to backdoor attacks. Recent studies have uncovered naturally...

Agentic AI Is Transforming Defense, But Only Secure IT Infrastructure Will Maximize It

Over the past several weeks, the cybersecurity community has been reminded how quickly frontier and agentic AI in defense networks can challenge our assumptions. When Anthropic's Claude Mythos model was made available to a limited set of organizations as a technical preview, it was reported that ...

CERT-In Recommends 12-Hour Patching for Internet-Facing Flaws Amid AI-Assisted Attacks

The Indian Computer Emergency Response Team CERT-In has issued new guidelines requiring organizations to patch critical security vulnerabilities in internet-exposed systems within 12 hours of being flagged where "feasible" to safeguard against potential threats stemming from threat actors' abuse ...

Cybersecurity of Electric Vehicle Charging Infrastructure: Recent Advances, Open Challenges, and Future Directions

Electric Vehicles EVs have emerged as significant disruptors in the transportation sector over the past decade. Their growing popularity and adoption are accompanied by capital expenditures to deploy charging infrastructure. EV charging infrastructure sits at the intersection of the power grid, t...

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

Automated detection of vulnerability-fixing commits VFCs is critical for timely security patch deployment, as advisory databases lag patch releases by a median of 25 days and many fixes never receive advisories. We present a comprehensive evaluation of code language model based VFC detection...

The Governance Gap: How the EU AI Act Makes API Security a Compliance Imperative

Your legal team just handed you a 400-page document and said "figure out compliance." The EU AI Act is live, your organization falls under its scope, which is broader than many expect. Even non‑EU companies must comply if their AI systems are used, deployed, or produce effects within the European...