paper-with-me

Papers

Better Trigger Inversion Optimization in Backdoor Scanning

2022-01-01 · CVPR 2022 1 · Guanhong Tao, Guangyu Shen, Yingqi Liu, Shengwei An, QiuLing Xu, Shiqing Ma, Pan Li, Xiangyu Zhang

Backdoor attacks aim to cause misclassification of a subject model by stamping a trigger to inputs. Backdoors could be injected through malicious training and naturally exist. Deriving backdoor trigger for a subject model is critical to both attack and defense. A popular trigger inversion method is by optimization. Existing methods are based on finding a smallest trigger that can uniformly flip a set of input samples by minimizing a mask. The mask defines the set of pixels that ought to be perturbed. We develop a new optimization method that directly minimizes individual pixel changes, without using a mask. Our experiments show that compared to existing methods, the new one can generate triggers that require a smaller number of input pixels to be perturbed, have a higher attack success rate, and are more robust. They are hence more desirable when used in real-world attacks and more effective when used in defense. Our method is also more cost-effective.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

FLIP https://developer.nvidia.com/blog/flip-a-difference-evaluator-for-alternating-images/

Similar Papers 제목 키워드 기반

TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models

2023-08-07 · ICCV 2023 1 · Indranil Sur, Karan Sikka, Matthew Walmer, Kaushik Koneripalli 외

We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization). Recent work arXiv:2112.07668 has demonstrated successful backdoor attacks on multimodal models for the Visual Question…

backdoor defenseobject-detectionObject DetectionQuestion Answering+1

DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion

2025-07-30 · Hossein Mirzaei, Zeinab Taghavi, Sepehr Rezaee, Masoud Hadi 외 arxiv

Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applica…

Object Detection

UNICORN: A Unified Backdoor Trigger Inversion Framework

2023-04-05 · Zhenting Wang, Kai Mei, Juan Zhai, Shiqing Ma

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effe…

Backdoor Attack

Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense

2022-02-11 · Guangyu Shen, Yingqi Liu, Guanhong Tao, QiuLing Xu 외

We develop a novel optimization method for NLPbackdoor inversion. We leverage a dynamically reducing temperature coefficient in the softmax function to provide changing loss landscapes to the optimizer such that the proc…

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering

2023-01-29 · Rui Zhu, Di Tang, Siyuan Tang, Guanhong Tao 외

Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-ba…

Backdoor Attack