TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning

Deep reinforcement learning DRL has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to...

Malicious code in meteor-react-component (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 10edb5e94e2b6aede51af9b2525726341571187cb32e9a56e9b86639c7130341 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Your Agent Can Defend Itself against Backdoor Attacks

Despite their growing adoption across domains, large language model LLM-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific...

WGLE:Backdoor-Free and Multi-Bit Black-Box Watermarking for Graph Neural Networks

Graph Neural Networks GNNs are increasingly deployed in graph-related applications, making ownership verification critical to protect their intellectual property against model theft. Fingerprinting and black-box watermarking are two main methods. However, the former relies on determining model...

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Vision Language Models VLMs have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of...

macOS LaunchDaemon iOS 17.2 - Privilege Escalation

!/usr/bin/env python3 Exploit Title: macOS LaunchDaemon iOS 17.2 - Privilege Escalation Author: Mohammed Idrees Banyamer @banyamersecurity GitHub: https://github.com/mbanyamer Date: 2025-05-31 Tested on: macOS Sonoma 14.x ARM64 / x8664 CVE: CVE-2025-24085 Type: Local Privilege Escalation Platform...

Robust Anti-Backdoor Instruction Tuning in LVLMs

Large visual language models LVLMs have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually developed for single-modal visual or language models under...

Heterogeneous Graph Backdoor Attack

Heterogeneous Graph Neural Networks HGNNs excel in modeling complex, multi-typed relationships across diverse domains, yet their vulnerability to backdoor attacks remains unexplored. To address this gap, we conduct the first investigation into the susceptibility of HGNNs to existing graph backdoo...

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Model merging for Large Language Models LLMs directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on open-source platforms, model merging is susceptible to...

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations manifesting in excessive reliance on training data, poor...

MixBridge: Heterogeneous Image-To-Image Backdoor Attack through Mixture of Schrödinger Bridges

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap...

RADEP: a Resilient Adaptive Defense Framework against Model Extraction Attacks

Machine Learning as a Service MLaaS enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks, where adversaries repeatedly query the application programming...

CVE-2025-48415

A USB backdoor feature can be triggered by attaching a USB drive that contains specially crafted "salia.ini" files. The .ini file can contain several "commands" that could be exploited by an attacker to export or modify the device configuration, enable an SSH backdoor or perform other...

CVE-2025-48413

The /etc/passwd and /etc/shadow files reveal hard-coded password hashes for the operating system "root" user. The credentials are shipped with the update files. There is no option for deleting or changing their passwords for an enduser. An attacker can use the credentials to log into the device...

CVE-2024-22083

An issue was discovered in Elspec G5 digital fault recorder versions 1.1.4.15 and before. A hardcoded backdoor session ID exists that can be used for further access to the device, including reconfiguration tasks...

CVE-2023-26243

An issue was discovered in the Hyundai Gen5WL in-vehicle infotainment system AEEPEEUR.S5WL001.001.211214. The decryption binary used to decrypt firmware files has an information leak that allows an attacker to read the AES key and initialization vector from memory. An attacker may exploit this to...

CVE-2023-42143

Missing Integrity Check in Shelly TRV 20220811-152343/v2.1.8@5afc928c allows malicious users to create a backdoor by redirecting the device to an attacker-controlled machine which serves the manipulated firmware file. The device is updated with the manipulated firmware...

CVE-2023-23771

Motorola MBTS Base Radio accepts hard-coded backdoor password. The Motorola MBTS Base Radio Man Machine Interface MMI, allowing for service technicians to diagnose and configure the device, accepts a hard-coded backdoor password that cannot be changed or disabled...

CVE-2023-23770

Motorola MBTS Site Controller accepts hard-coded backdoor password. The Motorola MBTS Site Controller Man Machine Interface MMI, allowing for service technicians to diagnose and configure the device, accepts a hard-coded backdoor password that cannot be changed or disabled...

CVE-2023-6614

A vulnerability classified as problematic was found in Typecho 1.2.1. Affected by this vulnerability is an unknown functionality of the file /admin/manage-pages.php of the component Page Handler. The manipulation leads to backdoor. The attack can be launched remotely. The exploit has been disclos...