Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments

With the growing integration of vision-language models VLMs, mobile agents are now widely used for tasks like UI automation and camera-based user assistance. These agents are often fine-tuned on limited user-generated datasets, leaving them vulnerable to covert threats during the training process...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

Exploit for Embedded Malicious Code in Tukaani Xz

Threat Intelligence Report: CVE-2024-3094 – XZ Utils Backdoor...

Probe Before You Talk: Towards Black-Box Defense against Backdoor Unalignment for Large Language Models

Backdoor unalignment attacks against Large Language Models LLMs enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of LLMs in the real-world Large Language Model as a Service...

CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks

Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated to specific malicious behavior. Various backdoor detection methods depend on...

Malicious code in react-svg-plugin (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware af2a1717363aad3bb129687fc2526ded4d96a8d7e578862b6d400cf5864e1985 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Google Chrome Zero-Day CVE-2025-2783 Exploited by TaxOff to Deploy Trinper Backdoor

A now-patched security flaw in Google Chrome was exploited as a zero-day by a threat actor known as TaxOff to deploy a backdoor codenamed Trinper. The attack, observed in mid-March 2025 by Positive Technologies, involved the use of a sandbox escape vulnerability tracked as CVE-2025-2783 CVSS scor...

Use of Hard-coded Credentials

Overview Affected versions of this package are vulnerable to Use of Hard-coded Credentials for the Service Account. An attacker could use the Service Account as a backdoor to the system using the leaked credentials. Remediation Upgrade openc3 to version 6.0.2 or higher. References - GitHub Commit...

TED-LaST: Towards Robust Backdoor Defense against Adaptive Attacks

Deep Neural Networks DNNs are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics TED has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be...

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...