paper-with-me

홈 › Papers

Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger

2023-02-28 · CVPR 2023 1 · Yi Yu, YuFei Wang, Wenhan Yang, Shijian Lu, Yap-Peng Tan, Alex C. Kot

Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns added to the input can lead to malicious behavior of the models. In this paper, we present a novel backdoor attack with multiple triggers against learned image compression models. Motivated by the widely used discrete cosine transform (DCT) in existing compression systems and standards, we propose a frequency-based trigger injection model that adds triggers in the DCT domain. In particular, we design several attack objectives for various attacking scenarios, including: 1) attacking compression quality in terms of bit-rate and reconstruction quality; 2) attacking task-driven measures, such as down-stream face recognition and semantic segmentation. Moreover, a novel simple dynamic loss is designed to balance the influence of different loss terms adaptively, which helps achieve more efficient training. Extensive experiments show that with our trained trigger injection models and simple modification of encoder parameters (of the compression model), the proposed attack can successfully inject several backdoors with corresponding triggers in a single image compression model.

📄 PDF Abstract BibTeX arXiv:2302.14677

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor AttackFace RecognitionImage CompressionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Discrete Cosine Transform Discrete Cosine Transform (DCT) is an orthogonal transformation method that decomposes an image to its spatial frequency spectrum. It expresses a finite sequence of data…

Similar Papers 제목 키워드 기반

Compression-Resistant Backdoor Attack against Deep Neural Networks

2022-01-03 · Mingfu Xue, Xin Wang, Shichang Sun, Yushu Zhang 외

In recent years, many backdoor attacks based on training data poisoning have been proposed. However, in practice, those backdoor attacks are vulnerable to image compressions. When backdoor instances are compressed, the f…

Backdoor AttackData PoisoningImage Compression

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks

2025-06-12 · Xiaoxing Mo, Yuxuan Cheng, Nan Sun, Leo Yu Zhang 외

Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics (TED) has recently emerged as …

backdoor defenseData Poisoning

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

2020-02-26 · Binghui Wang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…

Backdoor Attack

Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks

2022-03-07 · Siddhartha Datta, Nigel Shadbolt

Recent exploration of the multi-agent backdoor attack demonstrated the backfiring effect, a natural defense against backdoor attacks where backdoored inputs are randomly classified. This yields a side-effect of low accur…

Backdoor Attack

Backdooring and Poisoning Neural Networks with Image-Scaling Attacks

2020-03-19 · Erwin Quiring, Konrad Rieck

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the …