Deep Learning Backdoor Defense via Adaptive Trigger Collisions in Latent Space

Xiong, Zixun (ORCID:0009000473182084); Wang, Hao (ORCID:0000000214442657); Li, Jian (ORCID:0000000336423569); Hua, Yang (ORCID:000000015536503X); Pan, Miao (ORCID:0000000321384413); Du, Xiaojiang (ORCID:0000000342359671)

doi:10.1145/3779208.3806081

skip to main content

An official website of the United States government Here's how you know

Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, August 13 until 12:00 AM ET on Friday, August 14 due to maintenance. We apologize for the inconvenience.

Citation Details

This content will become publicly available on June 1, 2027

Deep Learning Backdoor Defense via Adaptive Trigger Collisions in Latent Space

Award ID(s):: 2332638

PAR ID:: 10696981

Author(s) / Creator(s):: Xiong, Zixun; Wang, Hao; Li, Jian; Hua, Yang; Pan, Miao; Du, Xiaojiang

Publisher / Repository:: ACM

Date Published:: 2026-06-01

ISBN:: 9798400723568

Page Range / eLocation ID:: 591 to 607

Format(s):: Medium: X

Location:: Bangalore India

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
This content will become publicly available on June 1, 2027
Conference Paper:
https://doi.org/10.1145/3779208.3806081

More Like this