CVE-2026-72671

A Kibana Machine Learning capability that removes a saved object from the current space accepts machine learning trained models as a target, but it verifies only the privileges that apply to anomaly detection jobs and data frame analytics jobs. A user whose role grants create anomaly detection jo...

Kibana 8.19.20, 9.4.5, 9.5.1 Security Update (ESA-2026-126)

Authorization Bypass Through User-Controlled Key in Kibana Leading to Cross-Space Access to Machine Learning Trained Models Description: Authorization Bypass Through User-Controlled Key CWE-639 in Kibana can lead to unauthorized cross-space access via Accessing Functionality Not Properly...

inspect_petri v3.1.0

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

Sovereign by Necessity? Frontier AI Export Controls, Cyber Security, and the Limits of National AI Capability

A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political will to decide which other countries may use these systems. In June 2026 the United States required a leading developer to...

Adversarial Robustness in Smishing Detection: A Comparative Analysis of Adversarial Fragility in Classical Vs. Transformer-Based Detection Systems

Smishing detection systems are commonly trained and evaluated on clean, monolingual text. In low-resource settings, however, attackers frequently circumvent these systems through character obfuscation, cross-lingual code-switching, and structural perturbation. This study evaluates adversarial...

CVE-2026-73655: Improper Authentication

Trigger.dev is a platform for building and deploying fully managed AI agents and workflows. Prior to 4.5.2, addGoogleStrategy in apps/webapp/app/services/googleAuth.server.ts passes a Google profile email to findOrCreateGoogleUser in apps/webapp/app/models/user.server.ts without requiring Google'...

CVE-2026-72642: Use of Out-of-range Pointer Offset

The native inference process that Elasticsearch uses to evaluate uploaded machine learning models accepts a model operation that computes a memory address from an offset supplied inside the model, without validating that the offset stays within the bounds of the underlying storage. A user with th...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

CVE-2026-21400 identifies a protection mechanism failure in Intel(R) AI Reference Models before version v3.4.1 when operating in Ring 3 (User Applications). The issue could allow an escalation of privilege where an unprivileged software adversary, with a privileged user and low attack complexity,...

EUVD-2026-56516

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

CVE-2026-21400: Protection Mechanism Failure

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

PT-2026-70325

Protection mechanism failure for some IntelR AI Reference Models before version v3.4.1 within Ring 3: User Applications may allow an escalation of privilege. Unprivileged software adversary with a privileged user combined with a low complexity attack may enable escalation of privilege. This resul...

Intel® AI Reference Models Software Advisory

Summary: A potential security vulnerability for some Intel® AI Reference Models software may allow escalation of privilege. Intel is releasing software updates to mitigate this potential vulnerability. Vulnerability Details: CVEID: CVE-2026-21400 Description: Protection mechanism failure for some...

Kimsuky Builds Offline AI Stack to Boost Phishing and Automate Malware Development

North Korea's state hackers are no longer content to type prompts into public chatbots. One of the country's main espionage groups has begun running artificial intelligence AI offline on its own servers, connecting document-search tools to files in its possession, and collecting the software part...

CVE-2026-12570

A vulnerability in keras-team/keras versions = 3.15.0 allows for a denial of service DoS attack when loading malicious .keras model files via the keras.models.loadmodel function. The H5IOStore.getitem method in keras/src/saving/savinglib.py does not validate the shape or size of datasets, leading...

CVE-2026-12570

A flaw was found in Keras. When loading malicious .keras model files using the keras.models.loadmodel function, the H5IOStore.getitem method does not validate the shape or size of datasets. This can lead to unbounded memory allocation, allowing a malicious actor to trigger an out-of-memory...

CVE-2026-12570 Denial of Service via HDF5 Shape Bomb in keras.models.load_model() in keras-team/keras

A vulnerability in keras-team/keras versions = 3.15.0 allows for a denial of service DoS attack when loading malicious .keras model files via the keras.models.loadmodel function. The H5IOStore.getitem method in keras/src/saving/savinglib.py does not validate the shape or size of datasets, leading...