Cover Image

Activation Functions Considered Harmful: Recovering Neural Network Weights through Controlled Channels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Spielman, Jesse, Oswald, David, Ryan, Mark, Van Bulck, Jo
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
by: Diaa, Abdulrahman, et al.
Published: (2023)

TrEEStealer: Stealing Decision Trees via Enclave Side Channels
by: Sander, Jonas, et al.
Published: (2026)

The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
by: Lintelo, Jona te, et al.
Published: (2024)

Discovering Command and Control Channels Using Reinforcement Learning
by: Wang, Cheng, et al.
Published: (2024)

On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel
by: Shukla, Shubhi, et al.
Published: (2022)

Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
by: Eggen, Marte, et al.
Published: (2026)

A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection
by: Jiang, Laura, et al.
Published: (2025)

Recovering Labels from Local Updates in Federated Learning
by: Chen, Huancheng, et al.
Published: (2024)

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
by: Yao, Yuan, et al.
Published: (2025)

Synthetic Trajectory Generation Through Convolutional Neural Networks
by: Merhi, Jesse, et al.
Published: (2024)

Machine Learning-Based Cyberattack Detection and Identification for Automatic Generation Control Systems Considering Nonlinearities
by: Shabar, Nour M., et al.
Published: (2025)

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

Compact: Approximating Complex Activation Functions for Secure Computation
by: Islam, Mazharul, et al.
Published: (2023)

Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
by: Ioniţă, Alexandru, et al.
Published: (2025)

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

Supervised Robustness-preserving Data-free Neural Network Pruning
by: Meng, Mark Huasong, et al.
Published: (2022)

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
by: Sasnauskas, Paulius, et al.
Published: (2025)

Approaching the Harm of Gradient Attacks While Only Flipping Labels
by: El-Kabid, Abdessamad, et al.
Published: (2025)

FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
by: Zhang, Xiangyu, et al.
Published: (2025)

Test-Time Collective Action: Proxy-Based Perturbations for Correcting Algorithmic Harms
by: Bhange, Meghana, et al.
Published: (2026)

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
by: Rashid, Md Rafi Ur, et al.
Published: (2023)

Monitor and Recover: A Paradigm for Future Research on Distribution Shift in Learning-Enabled Cyber-Physical Systems
by: Lin, Vivian, et al.
Published: (2025)

ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
by: Gong, Zirui, et al.
Published: (2026)

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills
by: Hsu, Chia-Yi, et al.
Published: (2026)

Certified Unlearning for Neural Networks
by: Koloskova, Anastasia, et al.
Published: (2025)

Residual Random Neural Networks
by: Andrecut, M.
Published: (2024)

DP-SGD Without Clipping: The Lipschitz Neural Network Way
by: Bethune, Louis, et al.
Published: (2023)

Unveiling ECC Vulnerabilities: LSTM Networks for Operation Recognition in Side-Channel Attacks
by: Battistello, Alberto, et al.
Published: (2025)

Byzantine Failures Harm the Generalization of Robust Distributed Learning Algorithms More Than Data Poisoning
by: Boudou, Thomas, et al.
Published: (2025)

Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design
by: Eshuijs, Leon, et al.
Published: (2026)

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?
by: Wen, Rui, et al.
Published: (2024)

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
by: Shukla, Shubhi, et al.
Published: (2024)

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

On Stealing Graph Neural Network Models
by: Podhajski, Marcin, et al.
Published: (2025)

Graph Neural Network Explanations are Fragile
by: Li, Jiate, et al.
Published: (2024)

Efficient Jailbreaking of Large Models by Freeze Training: Lower Layers Exhibit Greater Sensitivity to Harmful Content
by: Shen, Hongyuan, et al.
Published: (2025)

Differentially Private Release and Learning of Threshold Functions
by: Bun, Mark, et al.
Published: (2015)

Learning Nonlinearity of Boolean Functions: An Experimentation with Neural Networks
by: Ranga, Sriram, et al.
Published: (2025)

Cryptographic Backdoor for Neural Networks: Boon and Bane
by: Ngo, Anh Tu, et al.
Published: (2025)

Indiscriminate Data Poisoning Attacks on Neural Networks
by: Lu, Yiwei, et al.
Published: (2022)