aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDataset
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI Sec Watch

The security intelligence platform for AI teams

AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.

[TOTAL_TRACKED]
2,657
[LAST_24H]
7
[LAST_7D]
152
Daily BriefingMonday, March 30, 2026
>

Anthropic's Leaked "Mythos" Model Raises Dual-Use Security Concerns: An unreleased Anthropic AI model called Mythos was accidentally exposed through a configuration error, revealing advanced reasoning and coding abilities specifically aimed at cybersecurity. The model's improved capability to find and exploit software vulnerabilities, plus its ability to autonomously fix its own code problems, could enable both more sophisticated cyberattacks and better defenses.

>

Mistral Secures $830M for European AI Data Center: French AI startup Mistral raised $830 million in debt financing to build a Paris-area data center with thousands of Nvidia GPUs (specialized chips used for AI training) to train its large language models, aiming for 200 MW of European computing capacity by 2027.

Latest Intel

page 223/266
VIEW ALL
01

CVE-2022-35995: TensorFlow is an open source platform for machine learning. When `AudioSummaryV2` receives an input `sample_rate` with m

security
Sep 16, 2022

TensorFlow (an open source machine learning platform) has a vulnerability in its `AudioSummaryV2` function where passing a `sample_rate` input with multiple elements causes a CHECK failure, which can be exploited to trigger a denial of service attack (making the system unavailable by overloading it).

Critical This Week5 issues
critical

CVE-2025-15379: A command injection vulnerability exists in MLflow's model serving container initialization code, specifically in the `_

CVE-2025-15379NVD/CVE DatabaseMar 30, 2026
Mar 30, 2026
>

Critical Command Injection in MLflow Model Deployment: MLflow has a command injection vulnerability (where an attacker inserts malicious commands into input that gets executed) in its model serving code when deploying models with `env_manager=LOCAL`. The flaw allows attackers to execute arbitrary commands on deployment systems by inserting malicious content into the `python_env.yaml` file, which MLflow reads and uses in shell commands without validation. (CVE-2025-15379, Critical)

Fix: Update to TensorFlow 2.10.0 or the patched versions 2.9.1, 2.8.1, or 2.7.2. The fix is included in GitHub commit bf6b45244992e2ee543c258e519489659c99fb7f. No workarounds are available, so updating is required.

NVD/CVE Database
02

CVE-2022-35994: TensorFlow is an open source platform for machine learning. When `CollectiveGather` receives an scalar input `input`, it

security
Sep 16, 2022

TensorFlow (an open source platform for machine learning) has a vulnerability where a function called `CollectiveGather` crashes when it receives a scalar input (a single number rather than a list of numbers), allowing attackers to cause a denial of service attack (making the system unavailable). The issue has been fixed and will be released in upcoming versions of TensorFlow.

Fix: The fix is included in TensorFlow 2.10.0. It will also be backported (added to older versions still being supported) to TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2. Users should update to one of these patched versions. There are no known workarounds for this issue.

NVD/CVE Database
03

CVE-2022-35993: TensorFlow is an open source platform for machine learning. When `SetSize` receives an input `set_shape` that is not a 1

security
Sep 16, 2022

TensorFlow has a vulnerability where the `SetSize` function crashes when it receives an input called `set_shape` that is not a 1D tensor (a one-dimensional array of data). An attacker can exploit this crash to launch a denial of service attack (making the system unavailable to legitimate users).

Fix: Update TensorFlow to version 2.10.0 or apply patches to supported versions 2.9.1, 2.8.1, and 2.7.2. The fix is available in GitHub commit cf70b79d2662c0d3c6af74583641e345fc939467.

NVD/CVE Database
04

CVE-2022-35992: TensorFlow is an open source platform for machine learning. When `TensorListFromTensor` receives an `element_shape` of a

security
Sep 16, 2022

TensorFlow (an open source machine learning platform) has a bug in the `TensorListFromTensor` function where certain inputs cause a CHECK failure that can be exploited to crash the system. This vulnerability affects multiple versions of TensorFlow and has no known workarounds.

Fix: Update to TensorFlow 2.10.0, or apply the patch from GitHub commit 3db59a042a38f4338aa207922fa2f476e000a6ee. For users on older supported versions, updates are also available for TensorFlow 2.9.1, 2.8.1, and 2.7.2.

NVD/CVE Database
05

CVE-2022-35991: TensorFlow is an open source platform for machine learning. When `TensorListScatter` and `TensorListScatterV2` receive a

security
Sep 16, 2022

TensorFlow, an open-source machine learning platform, has a vulnerability where two functions (`TensorListScatter` and `TensorListScatterV2`) crash when given certain types of input, allowing attackers to cause a denial of service attack (making the system unavailable). The issue has been fixed and will be released in upcoming versions.

Fix: The issue has been patched in GitHub commit bb03fdf4aae944ab2e4b35c7daa051068a8b7f61. The fix will be included in TensorFlow 2.10.0, and will also be backported to TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2.

NVD/CVE Database
06

CVE-2022-36026: TensorFlow is an open source platform for machine learning. If `QuantizeAndDequantizeV3` is given a nonscalar `num_bits`

security
Sep 16, 2022

TensorFlow, an open source platform for machine learning, has a vulnerability in its `QuantizeAndDequantizeV3` function where passing a nonscalar `num_bits` input tensor (a multi-dimensional array instead of a single value) causes the program to crash, which can be exploited for a denial of service attack (making a service unavailable by overwhelming or crashing it). The issue affects multiple TensorFlow versions.

Fix: The issue has been patched in GitHub commit f3f9cb38ecfe5a8a703f2c4a8fead434ef291713. The fix will be included in TensorFlow 2.10.0 and will be backported to TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2. No workarounds are available; users should update to these patched versions.

NVD/CVE Database
07

CVE-2022-36019: TensorFlow is an open source platform for machine learning. If `FakeQuantWithMinMaxVarsPerChannel` is given `min` or `ma

security
Sep 16, 2022

TensorFlow (an open source machine learning platform) has a vulnerability where a specific function called `FakeQuantWithMinMaxVarsPerChannel` crashes when given certain types of input data, allowing attackers to cause a denial of service attack (making the system stop working). The developers have fixed the bug in their code.

Fix: The fix is included in TensorFlow 2.10.0, and will also be patched in earlier versions 2.9.1, 2.8.1, and 2.7.2. Users should update to one of these versions or later.

NVD/CVE Database
08

CVE-2022-36018: TensorFlow is an open source platform for machine learning. If `RaggedTensorToVariant` is given a `rt_nested_splits` lis

security
Sep 16, 2022

TensorFlow, an open source platform for machine learning, has a vulnerability where a function called `RaggedTensorToVariant` can crash if it receives incorrectly formatted input (tensors with ranks other than one). An attacker could use this crash to launch a denial of service attack (making the system unavailable).

Fix: The issue has been patched in GitHub commit 88f93dfe691563baa4ae1e80ccde2d5c7a143821. The fix is included in TensorFlow 2.10.0 and will also be backported to (applied to earlier versions of) TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2.

NVD/CVE Database
09

CVE-2022-35990: TensorFlow is an open source platform for machine learning. When `tf.quantization.fake_quant_with_min_max_vars_per_chann

security
Sep 16, 2022

A vulnerability in TensorFlow (an open source platform for machine learning) allows attackers to crash the system by sending specially formatted inputs to a specific function called `tf.quantization.fake_quant_with_min_max_vars_per_channel_gradient`, causing a denial of service attack (where a system becomes unavailable). The issue occurs when the function receives input parameters with the wrong structure (rank other than 1).

Fix: The vulnerability was patched in GitHub commit f3cf67ac5705f4f04721d15e485e192bb319feed. The fix is included in TensorFlow 2.10.0 and will also be backported (applied to older versions still receiving updates) to TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2. There are no known workarounds for this issue.

NVD/CVE Database
10

CVE-2022-35989: TensorFlow is an open source platform for machine learning. When `MaxPool` receives a window size input array `ksize` wi

security
Sep 16, 2022

TensorFlow (an open source platform for machine learning) has a vulnerability in its MaxPool function, which crashes when given a window size array with dimensions larger than the input data, allowing attackers to cause a denial of service attack (making the system unavailable). The issue has been patched and will be fixed in upcoming versions.

Fix: The fix is included in TensorFlow 2.10.0 and will be cherrypicked into TensorFlow 2.9.1, TensorFlow 2.8.1, and TensorFlow 2.7.2. Users should update to one of these patched versions. No workarounds are available.

NVD/CVE Database
Prev1...221222223224225...266Next
critical

CVE-2026-33873: Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assis

CVE-2026-33873NVD/CVE DatabaseMar 27, 2026
Mar 27, 2026
critical

Attackers exploit critical Langflow RCE within hours as CISA sounds alarm

CSO OnlineMar 27, 2026
Mar 27, 2026
critical

CVE-2025-53521: F5 BIG-IP Unspecified Vulnerability

CVE-2025-53521CISA Known Exploited VulnerabilitiesMar 26, 2026
Mar 26, 2026
critical

CISA: New Langflow flaw actively exploited to hijack AI workflows

BleepingComputerMar 26, 2026
Mar 26, 2026