Learn from model beyond fine-tuning: A survey
Foundation models (FM) have demonstrated remarkable performance across a wide range
of tasks (especially in the fields of natural language processing and computer vision) …
of tasks (especially in the fields of natural language processing and computer vision) …
Generalizable black-box adversarial attack with meta learning
In the scenario of black-box adversarial attack, the target model's parameters are unknown,
and the attacker aims to find a successful adversarial perturbation based on query feedback …
and the attacker aims to find a successful adversarial perturbation based on query feedback …
[图书][B] Adversarial robustness for machine learning
Adversarial Robustness for Machine Learning summarizes the recent progress on this topic
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
Waveform level adversarial example generation for joint attacks against both automatic speaker verification and spoofing countermeasures
X Zhang, X Zhang, W Liu, X Zou, M Sun… - Engineering Applications of …, 2022 - Elsevier
Adversarial examples crafted to deceive Automatic Speaker Verification (ASV) systems have
attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV …
attracted a lot of attention when studying the vulnerability of ASV. However, real-world ASV …
DifAttack: Query-Efficient Black-Box Adversarial Attack via Disentangled Feature Space
This work investigates efficient score-based black-box adversarial attacks with high Attack
Success Rate (ASR) and good generalizability. We design a novel attack method based on …
Success Rate (ASR) and good generalizability. We design a novel attack method based on …
Black-box Adversarial Attacks Against Image Quality Assessment Models
The goal of No-Reference Image Quality Assessment (NR-IQA) is to predict the perceptual
quality of an image in line with its subjective evaluation. To put the NR-IQA models into …
quality of an image in line with its subjective evaluation. To put the NR-IQA models into …
Taxonomy Driven Fast Adversarial Training
Adversarial training (AT) is an effective defense method against gradient-based attacks to
enhance the robustness of neural networks. Among them, single-step AT has emerged as a …
enhance the robustness of neural networks. Among them, single-step AT has emerged as a …
Generation of black-box adversarial attacks using many independent objective-based algorithm for testing the robustness of deep neural networks
O Sahin - Applied Soft Computing, 2024 - Elsevier
Deep neural networks (DNNs) have become increasingly ubiquitous in our daily lives,
finding applications in areas such as image recognition, voice recognition, and natural …
finding applications in areas such as image recognition, voice recognition, and natural …
Meta Security Metric Learning for Secure Deep Image Hiding
Deep Image Hiding (DIH) aims to imperceptibly hide images within image. To improve its
security performance, some DIH methods design Security Metrics (SMs) to guide the …
security performance, some DIH methods design Security Metrics (SMs) to guide the …
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross Domain
This work investigates efficient score-based black-box adversarial attacks with a high Attack
Success Rate (ASR) and good generalizability. We design a novel attack method based on …
Success Rate (ASR) and good generalizability. We design a novel attack method based on …