TorchGeo Remote Code Execution Vulnerability

Impact TorchGeo 0.4–0.6.0 used an eval statement in its model weight API that could allow an unauthenticated, remote attacker to execute arbitrary commands. All platforms that expose torchgeo.models.getweight or torchgeo.trainers as an external API could be affected. Patches The eval statement wa...

📄 Google Keras 3.13.0 Denial of Service

A denial of service vulnerability exists in the HDF5 weight loading component of Google Keras versions 3.0.0 through 3.13.0 on all platforms. The vulnerability is caused by the absence of any validation or throttling when processing HDF5 dataset shape metadata declared inside a .keras archive...

Before You Hand over the Wheel: Evaluating LLMs for Security Incident Analysis

Security incident analysis SIA poses a major challenge for security operations centers, which must manage overwhelming alert volumes, large and diverse data sources, complex toolchains, and limited analyst expertise. These difficulties intensify because incidents evolve dynamically and require...

CVE-2026-2292 Morkva UA Shipping <= 1.7.9 - Authenticated (Administrator+) Stored Cross-Site Scripting via 'Weight, kg' Field

The Morkva UA Shipping plugin for WordPress is vulnerable to Stored Cross-Site Scripting via admin settings in all versions up to, and including, 1.7.9 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with administrator-level...

WordPress Morkva UA Shipping plugin <= 1.7.9 - Authenticated (Administrator+) Stored Cross-Site Scripting via 'Weight, kg' Field vulnerability

Authenticated Administrator+ Stored Cross-Site Scripting via 'Weight, kg' Field vulnerability discovered by Phap Nguyen Anh - FIS in WordPress Plugin Morkva UA Shipping versions = 1.7.9...

Kraken: Higher-Order EM Side-Channel Attacks on DNNs in near and Far Field

The multi-million dollar investment required for modern machine learning ML has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA...

Keras has a Local File Disclosure via HDF5 External Storage During Keras Weight Loading

Summary TensorFlow / Keras continues to honor HDF5 “external storage” and ExternalLink features when loading weights. A malicious .weights.h5 or a .keras archive embedding such weights can direct loadweights to read from an arbitrary readable filesystem path. The bytes pulled from that path...

GHSA-3M4Q-JMJ6-R34Q Keras has a Local File Disclosure via HDF5 External Storage During Keras Weight Loading

Summary TensorFlow / Keras continues to honor HDF5 “external storage” and ExternalLink features when loading weights. A malicious .weights.h5 or a .keras archive embedding such weights can direct loadweights to read from an arbitrary readable filesystem path. The bytes pulled from that path...

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largel...

Aegis: Towards Governance, Integrity, and Security of AI Voice Agents

With the rapid advancement and adoption of Audio Large Language Models ALLMs, voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial misuse still remain unexplored. While prior work has examined...

Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models LLMs and improve the overall trust in artificial intelligence AI systems. The tech giant's AI Security team said the scanner leverages three observable signals that ca...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

Inference-Time Backdoors Via Hidden Instructions in LLM Chat Templates

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat in this context is backdoor attacks, in which adversaries embed hidden behaviors in language models that activate under specific conditions. Previous work has assumed th...

DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers

The widespread adoption of Vision Transformers ViTs elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors into released checkpoints. Existing ViT backdoor attacks largely rely on poisoned-data training, while prior data-free attempts typically require...

Sockpuppetting: Jailbreaking LLMs without Optimization through Output Prefix Injection

As open-weight large language models LLMs increase in capabilities, safeguarding them against malicious prompts and understanding possible attack vectors becomes ever more important. While automated jailbreaking methods like GCG Zou et al., 2023 remain effective, they often require substantial...

Duplicate Advisory: Google Keras Allocates Resources Without Limits or Throttling in the HDF5 weight loading component

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mgx6-5cf9-rr43. This link is maintained to preserve external references. Original Description Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 throu...

GHSA-XFHX-R7WW-5995 Duplicate Advisory: Google Keras Allocates Resources Without Limits or Throttling in the HDF5 weight loading component

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-mgx6-5cf9-rr43. This link is maintained to preserve external references. Original Description Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 throu...

PYSEC-2026-73

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...

AZL-74631 CVE-2026-0897 affecting package keras for versions less than 3.3.3-6

Allocation of Resources Without Limits or Throttling in the HDF5 weight loading component in Google Keras 3.0.0 through 3.13.0 on all platforms allows a remote attacker to cause a Denial of Service DoS through memory exhaustion and a crash of the Python interpreter via a crafted .keras archive...