Rethinking the Reverse-engineering of Trojan Triggers

Oct-9-2025, 15:16:31 GMT–Neural Information Processing Systems

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-engineering methods only consider input space constraints, e.g.,

artificial intelligence, machine learning, natural language, (21 more...)

Neural Information Processing Systems

Oct-9-2025, 15:16:31 GMT

Conferences PDF

Add feedback

Country:
- Asia > Nepal (0.04)

Genre:
- Research Report > New Finding (0.68)

Industry:
- Information Technology > Security & Privacy (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.89)
    - Natural Language (1.00)
    - Representation & Reasoning (1.00)
    - Vision (1.00)
  - Security & Privacy (1.00)

Duplicate Docs Excel Report

Title
Rethinking the Reverse-engineering of Trojan Triggers

Similar Docs Excel Report more

Title	Similarity	Source
None found