Menu

  • Alerts
  • Incidents
  • News
  • APTs
  • Cyber Decoded
  • Cyber Hygiene
  • Cyber Review
  • Cyber Tips
  • Definitions
  • Malware
  • Threat Actors
  • Tutorials

Useful Tools

  • Password generator
  • Report an incident
  • Report to authorities
No Result
View All Result
CTF Hack Havoc
CyberMaterial
  • Education
    • Cyber Decoded
    • Definitions
  • Information
    • Alerts
    • Incidents
    • News
  • Insights
    • Cyber Hygiene
    • Cyber Review
    • Tips
    • Tutorials
  • Support
    • Contact Us
    • Report an incident
  • About
    • About Us
    • Advertise with us
Get Help
Hall of Hacks
  • Education
    • Cyber Decoded
    • Definitions
  • Information
    • Alerts
    • Incidents
    • News
  • Insights
    • Cyber Hygiene
    • Cyber Review
    • Tips
    • Tutorials
  • Support
    • Contact Us
    • Report an incident
  • About
    • About Us
    • Advertise with us
Get Help
No Result
View All Result
Hall of Hacks
CyberMaterial
No Result
View All Result
Home Alerts

SWARM Backdoor Attack Discovered

May 17, 2024
Reading Time: 2 mins read
in Alerts
SWARM Backdoor Attack Discovered

The use of pre-trained large vision transformer (ViT) models on extensive datasets has become common practice to enhance performance on downstream tasks. A recent study by cybersecurity analysts from Tsinghua University, Tencent Security Platform Department, Zhejiang University, Research Center of Artificial Intelligence, and Peng Cheng Laboratory has uncovered a novel backdoor attack named SWARM (Switchable Backdoor Attack Against Pre-trained Models). This attack exploits the Visual Prompting (VP) technique, which introduces learnable task-specific parameters while keeping the pre-trained backbone frozen, posing unexplored security risks.

SWARM utilizes a “switch” prompt token that can be attached or removed to toggle between clean and backdoor modes stealthily. The attack optimizes triggers, clean prompts, and switch tokens to ensure normal behavior in the clean mode and targeted misclassification in the backdoor mode. Experiments show that SWARM achieves a high attack success rate of 96% against Neural Attention Distillation (NAD) and over 97% against I-BAU, outperforming baseline attacks significantly.

In a cloud service scenario, threat actors, often acting as cloud service providers, can control prompt inputs while users submit task datasets and pre-trained models to their service. The attack’s effectiveness lies in its ability to predict correctly on clean samples and cause misclassification when the switch trigger is added, making it highly evasive. These findings underscore the urgent need for enhanced security measures and continued research into defense mechanisms to protect against such sophisticated backdoor attacks.

Reference:

  • SWARM Attack Reveals Vision Transformer Model Risks

Tags: Cyber AlertCyber Alerts 2024Cyber RiskCyber threatMay 2024SecuritySWARMTencentZhejiang University
ADVERTISEMENT

Related Posts

Fake PyPI Login Site Steals Credentials

Fake PyPI Login Site Steals Credentials

September 26, 2025
Fake PyPI Login Site Steals Credentials

Google Warns of BRICKSTORM Malware

September 26, 2025
Fake PyPI Login Site Steals Credentials

Hidden WordPress Backdoors Create Admins

September 26, 2025
BadIIS Malware Spreads Via SEO Poisoning

Hackers Target AWS and Steal Credentials

September 24, 2025
BadIIS Malware Spreads Via SEO Poisoning

SonicWall SMA100 Update Removes Rootkit

September 24, 2025
BadIIS Malware Spreads Via SEO Poisoning

BadIIS Malware Spreads Via SEO Poisoning

September 24, 2025

Latest Alerts

Fake PyPI Login Site Steals Credentials

Google Warns of BRICKSTORM Malware

Hidden WordPress Backdoors Create Admins

Hackers Target AWS and Steal Credentials

SonicWall SMA100 Update Removes Rootkit

BadIIS Malware Spreads Via SEO Poisoning

Subscribe to our newsletter

    Latest Incidents

    Indian Bank Transfer Records Exposed

    Chinese Cyberspies Hit US Defense Firms

    Neon App Shuts Down After Data Leak

    Boyd Gaming Reports Data Breach After Attack

    Morrisroe UK Company Hit By Cyber Attack

    GeoServer Flaw Breaches US Agency Network

    CyberMaterial Logo
    • About Us
    • Contact Us
    • Jobs
    • Legal and Privacy Policy
    • Site Map

    © 2025 | CyberMaterial | All rights reserved

    Welcome Back!

    Login to your account below

    Forgotten Password?

    Retrieve your password

    Please enter your username or email address to reset your password.

    Log In

    Add New Playlist

    No Result
    View All Result
    • Alerts
    • Incidents
    • News
    • Cyber Decoded
    • Cyber Hygiene
    • Cyber Review
    • Definitions
    • Malware
    • Cyber Tips
    • Tutorials
    • Advanced Persistent Threats
    • Threat Actors
    • Report an incident
    • Password Generator
    • About Us
    • Contact Us
    • Advertise with us

    Copyright © 2025 CyberMaterial