VulnWatch VulnWatch
← Back to dashboard
#

Model Poisoning

5 entries

Every Model Poisoning entry VulnWatch has indexed, sorted by publication date.

Subscribe to this tag's RSS feed

High nvd

CVE-2026-3840: A vulnerability in Kedro version 1.2.0 allows an attacker to exploit path traversal by providing a crafted version strin

A vulnerability in Kedro version 1.2.0 allows an attacker to exploit path traversal by providing a crafted version string. The `_get_versioned_path()` method in `kedro/io/core.py` directly interpolate...

Model Poisoning data poisoning
7.1
CVSS
1 week ago
Unknown rss_securityweek

Hacker Conversations: Joey Melo on Hacking AI

AI red team specialist details his methods for manipulating AI guardrails through jailbreaking and data poisoning, helping developers harden machine learning models. The post Hacker Conversations: Joe...

Prompt Injection Model Poisoning machine learning data poisoning jailbreak
1 month ago
High github

WWBN AVideo has CSRF in configurationUpdate.json.php Enables Full Site Configuration Takeover Including Encoder URL and SMTP Credentials

## Summary `objects/configurationUpdate.json.php` (also routed via `/updateConfig`) persists dozens of global site settings from `$_POST` but protects the endpoint only with `User::isAdmin()`. It doe...

Model Poisoning data poisoning
8.3
CVSS
2 months ago
High github

Kedro: Path Traversal in versioned dataset loading via unsanitized version string

### Impact The `_get_versioned_path()` method in kedro/io/core.py constructs filesystem paths by directly interpolating user-supplied version strings without sanitization. Because version strings are...

Model Poisoning data poisoning
7.1
CVSS
2 months ago
Low osv

Undefined Behavior in mlflow

A vulnerability in mlflow/mlflow version 2.11.1 allows attackers to create multiple models with the same name by exploiting URL encoding. This flaw can lead to Denial of Service (DoS) as an authentica...

3.1
CVSS
2 years ago