Imagen de Portada

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Prato, Tahmid Hasan, Kim, Seijoon, Chen, Lizhong, Hong, Sanghyun
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
por: Coalson, Zachary, et al.
Publicado: (2026)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
por: Wen, Yuxin, et al.
Publicado: (2024)

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
por: Yang, Han, et al.
Publicado: (2025)

IF-GUIDE: Influence Function-Guided Detoxification of LLMs
por: Coalson, Zachary, et al.
Publicado: (2025)

Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations
por: Hong, Sanghyun, et al.
Publicado: (2025)

Fail-Closed Alignment for Large Language Models
por: Coalson, Zachary, et al.
Publicado: (2026)

Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
por: Coalson, Zachary, et al.
Publicado: (2024)

MADCAT: Combating Malware Detection Under Concept Drift with Test-Time Adaptation
por: Roh, Eunjin, et al.
Publicado: (2025)

Discovering Universal Activation Directions for PII Leakage in Language Models
por: Marchyok, Leo, et al.
Publicado: (2026)

RADAR: Defending RAG Dynamically against Retrieval Corruption
por: Chen, Ziyuan, et al.
Publicado: (2026)

Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons
por: Zehavi, Irad, et al.
Publicado: (2023)

Relationship between Uncertainty in DNNs and Adversarial Attacks
por: Ogonna, Mabel, et al.
Publicado: (2024)

Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience
por: Thakkar, Janvi, et al.
Publicado: (2023)

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
por: Feng, Shanglun, et al.
Publicado: (2024)

Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack
por: Jin, Zhibo, et al.
Publicado: (2024)

Flatness-aware Sequential Learning Generates Resilient Backdoors
por: Pham, Hoang, et al.
Publicado: (2024)

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training
por: Zmushko, Philip, et al.
Publicado: (2024)

Uncertainty-Aware Federated Learning for Cyber-Resilient Microgrid Energy Management
por: Babayomi, Oluleke, et al.
Publicado: (2025)

Reformulation is All You Need: Addressing Malicious Text Features in DNNs
por: Jiang, Yi, et al.
Publicado: (2025)

Privacy-aware Gaussian Process Regression
por: Tuo, Rui, et al.
Publicado: (2023)

PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
por: Zou, Wei, et al.
Publicado: (2024)

Certifiably Robust RAG against Retrieval Corruption
por: Xiang, Chong, et al.
Publicado: (2024)

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
por: Yao, Duanyi, et al.
Publicado: (2024)

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising
por: Hong, Sanghyun, et al.
Publicado: (2024)

SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy
por: Nahid, Md Mahadi Hasan, et al.
Publicado: (2024)

Mitigating Error Amplification in Fast Adversarial Training
por: Zhao, Mengnan, et al.
Publicado: (2026)

Position: Towards Resilience Against Adversarial Examples
por: Dai, Sihui, et al.
Publicado: (2024)

SD-CGAN: Conditional Sinkhorn Divergence GAN for DDoS Anomaly Detection in IoT Networks
por: Onyeka, Henry, et al.
Publicado: (2025)

Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack
por: Meng, Nicole, et al.
Publicado: (2024)

Data Poisoning: An Overlooked Threat to Power Grid Resilience
por: Agah, Nora, et al.
Publicado: (2024)

How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?
por: Liu, Meiqi, et al.
Publicado: (2025)

Regression-aware Continual Learning for Android Malware Detection
por: Ghiani, Daniele, et al.
Publicado: (2025)

TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement
por: Fan, Xinxin, et al.
Publicado: (2026)

Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation
por: Longari, Stefano, et al.
Publicado: (2025)

DMRL: Data- and Model-aware Reward Learning for Data Extraction
por: Wang, Zhiqiang, et al.
Publicado: (2025)

Ditto: Quantization-aware Secure Inference of Transformers upon MPC
por: Wu, Haoqi, et al.
Publicado: (2024)

An Efficient Privacy-aware Split Learning Framework for Satellite Communications
por: Sun, Jianfei, et al.
Publicado: (2024)

Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach
por: Eliasof, Moshe, et al.
Publicado: (2023)

Development of an Edge Resilient ML Ensemble to Tolerate ICS Adversarial Attacks
por: Yao, Likai, et al.
Publicado: (2024)

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
por: Lian, Jiawei, et al.
Publicado: (2024)