Copertina

Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Takahashi, Tsubasa, Yamabe, Shojiro, Waseda, Futa, Sasaki, Kento
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
di: Yamabe, Shojiro, et al.
Pubblicazione: (2024)

Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models
di: Waseda, Futa, et al.
Pubblicazione: (2025)

Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models
di: Yamabe, Shojiro, et al.
Pubblicazione: (2025)

Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens
di: Anwar, Usman, et al.
Pubblicazione: (2024)

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps
di: Bouras, Stavros, et al.
Pubblicazione: (2026)

Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation
di: Yang, Kun, et al.
Pubblicazione: (2025)

One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy
di: Zhang, Jiacheng, et al.
Pubblicazione: (2025)

Differentially Private Attention Computation
di: Gao, Yeqi, et al.
Pubblicazione: (2023)

Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
di: Xin, Yuan, et al.
Pubblicazione: (2023)

Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes
di: Hamidi, Shayan Mohajer, et al.
Pubblicazione: (2024)

On the Robustness of Malware Detectors to Adversarial Samples
di: Salman, Muhammad, et al.
Pubblicazione: (2024)

Differentiable Adversarial Attacks for Marked Temporal Point Processes
di: Chakraborty, Pritish, et al.
Pubblicazione: (2025)

DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
di: Pulido-Cortázar, Daniel, et al.
Pubblicazione: (2025)

Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability
di: Li, Chenxi, et al.
Pubblicazione: (2024)

Taking off the Rose-Tinted Glasses: A Critical Look at Adversarial ML Through the Lens of Evasion Attacks
di: Eykholt, Kevin, et al.
Pubblicazione: (2024)

Trading Inference-Time Compute for Adversarial Robustness
di: Zaremba, Wojciech, et al.
Pubblicazione: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
di: Zhang, Junrui, et al.
Pubblicazione: (2025)

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
di: Hao, Yifan, et al.
Pubblicazione: (2024)

IDEA: Invariant Defense for Graph Adversarial Robustness
di: Tao, Shuchang, et al.
Pubblicazione: (2023)

Adversarial Robustness of Link Sign Prediction in Signed Graphs
di: Zhou, Jialong, et al.
Pubblicazione: (2024)

On the Adversarial Robustness of Graph Neural Networks with Graph Reduction
di: Wu, Kerui, et al.
Pubblicazione: (2024)

Adversarial Patterns: Building Robust Android Malware Classifiers
di: Bhusal, Dipkamal, et al.
Pubblicazione: (2022)

DPM: Clustering Sensitive Data through Separation
di: Liebenow, Johannes, et al.
Pubblicazione: (2023)

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
di: Jiang, Enyi, et al.
Pubblicazione: (2024)

Differentially Private Selection using Smooth Sensitivity
di: Chaves, Iago, et al.
Pubblicazione: (2025)

Adversarially-Aware Architecture Design for Robust Medical AI Systems
di: Gerhart, Alyssa, et al.
Pubblicazione: (2025)

Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
di: Wang, Yongyu
Pubblicazione: (2025)

Adversarially Robust Bloom Filters: Privacy, Reductions, and Open Problems
di: Tirmazi, Hayder
Pubblicazione: (2025)

Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
di: Fink, Xaver, et al.
Pubblicazione: (2026)

Testing Credibility of Public and Private Surveys through the Lens of Regression
di: Basu, Debabrota, et al.
Pubblicazione: (2024)

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
di: Zhang, Haobo, et al.
Pubblicazione: (2026)

AdvSGM: Differentially Private Graph Learning via Adversarial Skip-gram Model
di: Zhang, Sen, et al.
Pubblicazione: (2025)

Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory
di: Fu, Shaopeng, et al.
Pubblicazione: (2026)

Towards Explainable Federated Learning: Understanding the Impact of Differential Privacy
di: Oliveira, Júlio, et al.
Pubblicazione: (2026)

Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
di: Lyu, Saiyue, et al.
Pubblicazione: (2024)

Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing
di: Talluri, Abhijit
Pubblicazione: (2026)

Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers
di: Askarizadeh, Mohammad Javad, et al.
Pubblicazione: (2024)

Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
di: Angioni, Daniele, et al.
Pubblicazione: (2024)

Robust Semi-Supervised Temporal Intrusion Detection for Adversarial Cloud Networks
di: Chattopadhyay, Anasuya, et al.
Pubblicazione: (2026)

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
di: Wu, Jiapeng, et al.
Pubblicazione: (2023)