CodeGuard: a Generalized and Stealthy Backdoor Watermarking for Generative Code Models

Generative code models GCMs significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating effective digital copyright protection to prevent unauthorized lea...

SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning

Federated Learning FL has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenges, notably the threat of backdoor attacks. Existing backdoor strategies predominantly rely on end-to-end label...

CVE-2025-48469

Successful exploitation of the vulnerability could allow an unauthenticated attacker to upload firmware through a public update page, potentially leading to backdoor installation or privilege escalation...

CVE-2025-48469 Unauthenticated Firmware Upload

Successful exploitation of the vulnerability could allow an unauthenticated attacker to upload firmware through a public update page, potentially leading to backdoor installation or privilege escalation...

CVE-2025-48469 Unauthenticated Firmware Upload

Successful exploitation of the vulnerability could allow an unauthenticated attacker to upload firmware through a public update page, potentially leading to backdoor installation or privilege escalation...

CVE-2025-48469

CVE-2025-48469 is an unauthenticated firmware upload vulnerability widely described across multiple feeds. The initial entry states that a successful exploit could allow an unauthenticated attacker to upload firmware through a public update page, potentially enabling backdoor installation or priv...

OneClik: A ClickOnce-Based APT Campaign Targeting Energy, Oil and Gas Infrastructure

OneClik: A ClickOnce-Based APT Campaign Targeting Energy, Oil and Gas Infrastructure By Nico Paulo Yturriaga and Pham Duy Phuc · June 24, 2025 The Trellix Advanced Research Center has uncovered a sophisticated APT malware campaign that we’ve dubbed OneClik. It specifically targets the energy, oil...

Advantech多款产品 安全漏洞

The Advantech WISE-4010LAN, WISE-4050LAN, and WISE-4060LAN are all industrial automation controllers from Advantech of Taiwan, China. A file upload vulnerability exists in multiple Advantech products, which can be exploited by attackers to cause a backdoor installation or elevation of privilege...

China-linked LapDogs Campaign Drops ShortLeash Backdoor with Fake Certs

ShortLeash backdoor, used in the China-linked LapDogs campaign since 2023, enables stealth access, persistence, and data theft via compromised SOHO routers and fake certs...

VulnCheck KEV: CVE-2025-34033

An OS command injection vulnerability exists in the Blue Angel Software Suite running on embedded Linux devices via the pingaddr parameter in the webctrl.cgi script. The application fails to properly sanitize input before passing it to the system-level ping command. An authenticated attacker can...

PT-2025-26681 · Advantech +1 · Advantech Wireless Sensing/Equipment +6

Name of the Vulnerable Software and Affected Versions: The product name cannot be determined. Description: The issue allows an unauthenticated attacker to upload firmware through a public update page. This could potentially lead to backdoor installation or privilege escalation. Recommendations: A...

MEraser: an Effective Fingerprint Erasure Approach for Large Language Models

Large Language Models LLMs have become increasingly prevalent across various sectors, raising critical concerns about model ownership and intellectual property protection. Although backdoor-based fingerprinting has emerged as a promising solution for model authentication, effective attacks for...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

Investigating Vulnerabilities and Defenses against Audio-Visual Attacks: a Comprehensive Survey Emphasizing Multimodal Models

Multimodal large language models MLLMs, which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computation...

When Forgetting Triggers Backdoors: a Clean Unlearning Attack

Machine unlearning has emerged as a key component in ensuring Right to be Forgotten, enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set clean unlearning, it can be exploited for stealthy attacks that...

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...

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...

Exploit for Embedded Malicious Code in Tukaani Xz

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

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...

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...