paper-with-me

홈 › Papers

Corrupting Data to Remove Deceptive Perturbation: Using Preprocessing Method to Improve System Robustness

2022-01-05 · Hieu Le, Hans Walker, Dung Tran, Peter Chin

Although deep neural networks have achieved great performance on classification tasks, recent studies showed that well trained networks can be fooled by adding subtle noises. This paper introduces a new approach to improve neural network robustness by applying the recovery process on top of the naturally trained classifier. In this approach, images will be intentionally corrupted by some significant operator and then be recovered before passing through the classifiers. SARGAN -- an extension on Generative Adversarial Networks (GAN) is capable of denoising radar signals. This paper will show that SARGAN can also recover corrupted images by removing the adversarial effects. Our results show that this approach does improve the performance of naturally trained networks.

📄 PDF Abstract BibTeX arXiv:2201.01399

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Similar Papers 제목 키워드 기반

VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models

2026-06-10 · Chunlin Qiu, Ang Li, Tianxiao Huang, Ruilin Gan 외 arxiv

While Latent Diffusion Models (LDMs) have revolutionized visual synthesis, they are increasingly exploited for unauthorized mimicry of individuals. Existing defenses inject deceptive perturbations to steer the generated …

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

2024-01-10 · Evan Hubinger, Carson Denison, Jesse Mu, Mike Lambert 외

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system lear…

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

2024-12-22 · Yichen Wang, Yuxuan Chou, Ziqi Zhou, Hangtao Zhang 외

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect…

Disentanglement

ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization

2026-06-19 · Jiaming He, Jiashu Zhang, Guanyu Hou, Shuhan Ye 외 arxiv

Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such models to imitate a specific subject, style, …

Towards Deep Neural Network Architectures Robust to Adversarial Examples

2014-12-11 · Shixiang Gu, Luca Rigazio

Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking images as an example, such distortions are of…

Denoising