Copertina

Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shukla, Shubhi, Alam, Manaar, Mitra, Pabitra, Mukhopadhyay, Debdeep
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

"Energon": Unveiling Transformers from GPU Power and Thermal Side-Channels
di: Chaudhuri, Arunava, et al.
Pubblicazione: (2025)

Deep-Lock: Secure Authorization for Deep Neural Networks
di: Alam, Manaar, et al.
Pubblicazione: (2020)

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

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
di: Alam, Manaar, et al.
Pubblicazione: (2025)

Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
di: Yilmaz, Eda, et al.
Pubblicazione: (2024)

LLMPot: Dynamically Configured LLM-based Honeypot for Industrial Protocol and Physical Process Emulation
di: Vasilatos, Christoforos, et al.
Pubblicazione: (2024)

Transpose Attack: Stealing Datasets with Bidirectional Training
di: Amit, Guy, et al.
Pubblicazione: (2023)

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

Stealing Training Graphs from Graph Neural Networks
di: Lin, Minhua, et al.
Pubblicazione: (2024)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
di: Lou, Jiadong, et al.
Pubblicazione: (2025)

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles
di: Shukla, Shubhi, et al.
Pubblicazione: (2021)

Detecting Adversarial Examples
di: Mumcu, Furkan, et al.
Pubblicazione: (2024)

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

Transferability Ranking of Adversarial Examples
di: Levy, Mosh, et al.
Pubblicazione: (2022)

Stealix: Model Stealing via Prompt Evolution
di: Zhuang, Zhixiong, et al.
Pubblicazione: (2025)

Laundering AI Authority with Adversarial Examples
di: Zhang, Jie, et al.
Pubblicazione: (2026)

When and How to Fool Explainable Models (and Humans) with Adversarial Examples
di: Vadillo, Jon, et al.
Pubblicazione: (2021)

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

Revealing CNN Architectures via Side-Channel Analysis in Dataflow-based Inference Accelerators
di: Weerasena, Hansika, et al.
Pubblicazione: (2023)

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

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

Prompt Stealing Attacks Against Text-to-Image Generation Models
di: Shen, Xinyue, et al.
Pubblicazione: (2023)

SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge
di: Fenaux, Lucas, et al.
Pubblicazione: (2024)

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

Augmenting Parameter-Efficient Pre-trained Language Models with Large Language Models
di: Anand, Saurabh, et al.
Pubblicazione: (2026)

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity
di: Zhu, Zhihao, et al.
Pubblicazione: (2023)

Privacy Side Channels in Machine Learning Systems
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2023)

Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models
di: Beerens, Lucas, et al.
Pubblicazione: (2025)

DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks
di: Chen, Jinyin, et al.
Pubblicazione: (2024)

Improved Generation of Adversarial Examples Against Safety-aligned LLMs
di: Li, Qizhang, et al.
Pubblicazione: (2024)

Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective
di: Zhang, Andi, et al.
Pubblicazione: (2023)

Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
di: Wang, Bo, et al.
Pubblicazione: (2026)

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
di: Yoon, Do-hyeon, et al.
Pubblicazione: (2025)

Watermark Stealing in Large Language Models
di: Jovanović, Nikola, et al.
Pubblicazione: (2024)

Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
di: Zhang, Tianchen, et al.
Pubblicazione: (2024)

Comprehensive Survey on Adversarial Examples in Cybersecurity: Impacts, Challenges, and Mitigation Strategies
di: Li, Li
Pubblicazione: (2024)

A Review and Comparison of AI Enhanced Side Channel Analysis
di: Panoff, Max, et al.
Pubblicazione: (2024)

Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions
di: Yang, Yunfei, et al.
Pubblicazione: (2025)

Link Stealing Attacks Against Inductive Graph Neural Networks
di: Wu, Yixin, et al.
Pubblicazione: (2024)