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

Browse All

All tracked items across vulnerabilities, news, research, incidents, and regulatory updates.

to
Export CSV
3312 items

CVE-2024-5397: A vulnerability classified as critical was found in itsourcecode Online Student Enrollment System 1.0. Affected by this

mediumvulnerability
security
May 27, 2024
CVE-2024-5397

CVE-2024-5397 is a critical vulnerability in itsourcecode Online Student Enrollment System 1.0 that allows SQL injection (an attack where malicious code is inserted into database queries through user input). The flaw exists in the instructorSubjects.php file where the instructorId parameter is not properly protected, and an attacker can exploit it remotely with valid user credentials.

NVD/CVE Database

CVE-2024-4858: The Testimonial Carousel For Elementor plugin for WordPress is vulnerable to unauthorized modification of data due to a

mediumvulnerability
security
May 25, 2024
CVE-2024-4858

The Testimonial Carousel For Elementor WordPress plugin (versions up to 10.2.0) has a missing authorization check in the 'save_testimonials_option_callback' function, allowing unauthenticated attackers to modify data like OpenAI API keys without permission. This vulnerability is classified as CWE-862 (missing authorization, where a system doesn't verify that a user has permission to perform an action).

Robust governance for the AI Act: Insights and highlights from Novelli et al. (2024)

inforegulatory
policy
May 24, 2024

This overview discusses the European AI Act and the governance framework needed to implement it, focusing on the European Commission's responsibilities and the AI Office. Key tasks include establishing guidelines for classifying high-risk AI systems, defining what counts as significant modifications (changes that alter a system's risk level), and setting standards for transparency and enforcement across EU member states.

ChatGPT: Hacking Memories with Prompt Injection

mediumnews
securitysafety

CVE-2024-0453: The AI ChatBot plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check

mediumvulnerability
security
May 22, 2024
CVE-2024-0453

The AI ChatBot plugin for WordPress (up to version 5.3.4) has a security flaw where a function called openai_file_delete_callback lacks a capability check (verification that a user has permission to perform an action). This allows any authenticated user with subscriber-level access or higher to delete files from a connected OpenAI account without proper authorization.

CVE-2024-0452: The AI ChatBot plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check

mediumvulnerability
security
May 22, 2024
CVE-2024-0452

The AI ChatBot plugin for WordPress (up to version 5.3.4) has a missing capability check (a missing authorization check that verifies user permissions) in its file upload function, allowing authenticated users with basic subscriber access to upload files to a connected OpenAI account without proper permission verification. This vulnerability affects all versions through 5.3.4 and could let low-privilege attackers modify data on the linked OpenAI account.

CVE-2024-0451: The AI ChatBot plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on th

mediumvulnerability
security
May 22, 2024
CVE-2024-0451

The AI ChatBot plugin for WordPress has a security flaw in versions up to 5.3.4 where a function lacks a capability check (a security control that verifies a user has permission to perform an action). This allows authenticated users with subscriber-level access or higher to view files stored in a connected OpenAI account without authorization.

CVE-2023-52828: In the Linux kernel, the following vulnerability has been resolved: bpf: Detect IP == ksym.end as part of BPF program

mediumvulnerability
security
May 21, 2024
CVE-2023-52828

A vulnerability in the Linux kernel's BPF (Berkeley Packet Filter, a technology for running safe programs in the kernel) subsystem occurs when a BPF program ends with a call to bpf_throw (a function that terminates execution), causing the instruction pointer to point just past the program's boundary. This breaks stack unwinding (the process of tracking where an error originated across function calls), potentially causing a panic (system crash). The fix makes the kernel treat instruction pointers at the program boundary (IP == ksym.end) as part of the program, allowing reliable stack unwinding in these cases.

CVE-2021-47231: In the Linux kernel, the following vulnerability has been resolved: can: mcba_usb: fix memory leak in mcba_usb Syzbot

mediumvulnerability
security
May 21, 2024
CVE-2021-47231

A memory leak was found in the Linux kernel's SocketCAN driver for Microchip CAN BUS Analyzer Tool, where 20 USB coherent buffers (memory blocks allocated for direct USB communication) were allocated in the mcba_usb_start() function but never freed, causing memory to be wasted when the device disconnected. The issue occurred because the disconnect function simply stopped the USB requests without properly deallocating the coherent buffers.

Machine Learning Attack Series: Backdooring Keras Models and How to Detect It

infonews
securityresearch

CVE-2024-35791: In the Linux kernel, the following vulnerability has been resolved: KVM: SVM: Flush pages under kvm->lock to fix UAF in

highvulnerability
security
May 17, 2024
CVE-2024-35791

A use-after-free vulnerability (UAF, a bug where code tries to access memory that has already been freed) was found in the Linux kernel's KVM (virtual machine software) SVM (a CPU virtualization technology) module in the svm_register_enc_region() function. The vulnerability occurred because a cache flush operation was happening after releasing a lock, allowing another part of the program to delete the region data before the flush completed.

CVE-2024-4263: A broken access control vulnerability exists in mlflow/mlflow versions before 2.10.1, where low privilege users with onl

mediumvulnerability
security
May 16, 2024
CVE-2024-4263

MLflow (a tool for managing machine learning experiments) versions before 2.10.1 have a broken access control vulnerability where users with only EDIT permissions can delete artifacts (saved files or data from experiments) they shouldn't be able to delete. The bug happens because the system doesn't properly check permissions when users request to delete artifacts, even though the documentation says EDIT users should only be able to read and update, not delete.

CVE-2024-3848: A path traversal vulnerability exists in mlflow/mlflow version 2.11.0, identified as a bypass for the previously address

highvulnerability
security
May 16, 2024
CVE-2024-3848EPSS: 78.7%

CVE-2024-4318: The Tutor LMS plugin for WordPress is vulnerable to time-based SQL Injection via the ‘question_id’ parameter in versions

highvulnerability
security
May 16, 2024
CVE-2024-4318

The Tutor LMS plugin for WordPress (versions up to 2.7.0) has a time-based SQL injection vulnerability (a technique where attackers sneak malicious database commands into user input to extract data) in the 'question_id' parameter because the plugin doesn't properly clean user input or prepare its database queries. Attackers with Instructor-level permissions or higher can exploit this to extract sensitive information from the database.

CVE-2024-4279: The Tutor LMS – eLearning and online course solution plugin for WordPress is vulnerable to Insecure Direct Object Refere

mediumvulnerability
security
May 16, 2024
CVE-2024-4279

The Tutor LMS WordPress plugin (up to version 2.7.0) has a security flaw called IDOR (insecure direct object reference, where an attacker can access resources by guessing or manipulating ID numbers) that lets users with Instructor-level permissions delete any course without proper permission checks in the 'tutor_course_delete' function. This happens because the code doesn't validate which courses a user is allowed to delete.

CVE-2024-4181: A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the

criticalvulnerability
security
May 16, 2024
CVE-2024-4181

A command injection vulnerability (a flaw that lets attackers run unauthorized commands) exists in the RunGptLLM class of the llama_index library version 0.9.47, which connects applications to language models. The vulnerability uses the eval function (a tool that executes text as code) unsafely, potentially allowing a malicious LLM provider to run arbitrary commands and take control of a user's machine.

Pivot to the Clouds: Cookie Theft in 2024

infonews
security
May 16, 2024

A researcher examined browser remote debugging features as a potential method for stealing sensitive data like cookies, building on past work about cookie theft techniques. The post references Google's guidance on detecting browser data theft through Windows Event Logs and DPAPI (Data Protection API, a Windows system that encrypts sensitive information) calls, but focuses on exploring whether remote debugging could be used to bypass these detection methods.

CVE-2024-4397: The LearnPress – WordPress LMS Plugin plugin for WordPress is vulnerable to arbitrary file uploads due to missing file t

highvulnerability
security
May 14, 2024
CVE-2024-4397EPSS: 14.9%

CVE-2024-34440: Unrestricted Upload of File with Dangerous Type vulnerability in Jordy Meow AI Engine: ChatGPT Chatbot.This issue affect

criticalvulnerability
security
May 14, 2024
CVE-2024-34440

CVE-2024-34440 is an unrestricted file upload vulnerability (a security flaw that lets users upload files without proper checks on file type) in the Jordy Meow AI Engine: ChatGPT Chatbot plugin affecting versions through 2.2.63. This vulnerability could potentially allow attackers to upload dangerous files to a system, but no severity score has been assigned yet.

CVE-2024-0100: NVIDIA Triton Inference Server for Linux contains a vulnerability in the tracing API, where a user can corrupt system fi

mediumvulnerability
security
May 14, 2024
CVE-2024-0100

CVE-2024-0100 is a vulnerability in NVIDIA Triton Inference Server for Linux that allows a user to corrupt system files through the tracing API (a feature that tracks how the server runs). Successfully exploiting this vulnerability could cause denial of service (making the system unavailable) and data tampering (unauthorized changes to data).

Previous117 / 166Next
NVD/CVE Database

Fix: The source suggests that the Commission should adopt 'predetermined change management plans akin to those in medicine' to assess modifications to AI systems. These plans would be documents outlining anticipated changes (such as performance adjustments or shifts in intended use) and the methods for evaluating whether those changes substantially alter the system's risk level. The source also recommends that standard fine-tuning of foundation models (training adjustments to pre-existing AI models) should not be considered a significant modification unless safety layers are removed or other actions clearly increase risk.

EU AI Act Updates
May 22, 2024

ChatGPT's new memory feature, which lets the AI remember information across different chat sessions for a more personalized experience, can be exploited through indirect prompt injection (tricking an AI by hiding malicious instructions in its input). Attackers could manipulate ChatGPT into storing false information, biases, or unwanted instructions by injecting commands through connected apps like Google Drive, uploaded documents, or web browsing features.

Embrace The Red
NVD/CVE Database
NVD/CVE Database

Fix: A patch is available at https://plugins.trac.wordpress.org/changeset/3089461/chatbot/trunk/includes/openai/qcld-bot-openai.php. Users should update their AI ChatBot plugin to a version after 5.3.4.

NVD/CVE Database

Fix: Make bpf_prog_ksym_find treat IP == ksym.end as part of the BPF program, so that is_bpf_text_address returns true when such a case occurs, allowing reliable unwinding when the final instruction ends up being a call instruction.

NVD/CVE Database

Fix: All allocated buffers should be freed with usb_free_coherent() explicitly. The source notes that the same correct pattern for allocating and freeing coherent buffers is used in drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c.

NVD/CVE Database
May 18, 2024

This post examines how attackers can insert hidden malicious code into machine learning models (a technique called backdooring) through supply chain attacks, specifically targeting Keras models (a popular framework for building AI systems). The authors demonstrate this attack and then explore tools that can detect when a model has been compromised in this way.

Embrace The Red

Fix: Do the cache flush of converted pages in svm_register_enc_region() before dropping kvm->lock (release the lock only after the flush is complete, not before). This ensures the region and its page array cannot be freed by another task while the flush is still in progress.

NVD/CVE Database

Fix: Update mlflow to version 2.10.1 or later.

NVD/CVE Database

MLflow version 2.11.0 has a path traversal vulnerability (a security flaw where an attacker can access files outside intended directories) that bypasses a previous fix. An attacker can use a '#' character in artifact URLs to skip validation and read sensitive files like SSH keys and cloud credentials from the server's filesystem. The vulnerability exists because the application doesn't properly validate the fragment portion (the part after '#') of URLs before converting them to filesystem paths.

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database

Fix: This issue was fixed in version 0.10.13 of the llama_index library. Users should upgrade to version 0.10.13 or later.

NVD/CVE Database
Embrace The Red

LearnPress, a WordPress plugin for learning management systems, has a vulnerability (CVE-2024-4397) in versions up to 4.2.6.5 where the 'save_post_materials' function doesn't properly check file types before uploading. This means instructors and higher-level users could upload malicious files to the server, potentially leading to RCE (remote code execution, where attackers run arbitrary commands on a system they don't own).

NVD/CVE Database
NVD/CVE Database
NVD/CVE Database