Cover Image

Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kalavasis, Alkis, Karbasi, Amin, Oikonomou, Argyris, Sotiraki, Katerina, Velegkas, Grigoris, Zampetakis, Manolis
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the Computational Landscape of Replicable Learning
by: Kalavasis, Alkis, et al.
Published: (2024)

Optimal Learners for Realizable Regression: PAC Learning and Online Learning
by: Attias, Idan, et al.
Published: (2023)

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

Planting Undetectable Backdoors in Machine Learning Models
by: Goldwasser, Shafi, et al.
Published: (2022)

Replicable Learning of Large-Margin Halfspaces
by: Kalavasis, Alkis, et al.
Published: (2024)

On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability
by: Kalavasis, Alkis, et al.
Published: (2024)

On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse
by: Kalavasis, Alkis, et al.
Published: (2024)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
by: Mehrotra, Anay, et al.
Published: (2023)

Private Statistical Estimation via Truncation
by: Zampetakis, Manolis, et al.
Published: (2025)

Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
by: Choudhary, Sarthak, et al.
Published: (2026)

Smaller Confidence Intervals From IPW Estimators via Data-Dependent Coarsening
by: Kalavasis, Alkis, et al.
Published: (2024)

Transfer Learning Beyond Bounded Density Ratios
by: Kalavasis, Alkis, et al.
Published: (2024)

Prompt Obfuscation for Large Language Models
by: Pape, David, et al.
Published: (2024)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
by: An, Shengwei, et al.
Published: (2023)

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

Command-line Obfuscation Detection using Small Language Models
by: Outrata, Vojtech, et al.
Published: (2024)

Prediction-Augmented Trees for Reliable Statistical Inference
by: Kher, Vikram, et al.
Published: (2025)

On the Learning Curves of Revenue Maximization
by: Hanneke, Steve, et al.
Published: (2026)

Defending against Backdoor Attack on Deep Neural Networks
by: Cheng, Hao, et al.
Published: (2020)

What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness
by: Cai, Yang, et al.
Published: (2025)

PrivDiffuser: Privacy-Guided Diffusion Model for Data Obfuscation in Sensor Networks
by: Yang, Xin, et al.
Published: (2024)

DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks
by: Sui, Hao, et al.
Published: (2024)

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
by: Dong, Xuewen, et al.
Published: (2025)

Backdooring Masked Diffusion Language Models
by: Cao, Daniel Yiming, et al.
Published: (2026)

Amalgam: A Framework for Obfuscated Neural Network Training on the Cloud
by: Taki, Sifat Ut, et al.
Published: (2024)

On Union-Closedness of Language Generation
by: Hanneke, Steve, et al.
Published: (2025)

BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks
by: Puah, Yi Hao, et al.
Published: (2024)

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
by: Yao, Duanyi, et al.
Published: (2024)

Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
by: Gosch, Lukas, et al.
Published: (2024)

An Undetectable Watermark for Generative Image Models
by: Gunn, Sam, et al.
Published: (2024)

Learning Mixture Models via Efficient High-dimensional Sparse Fourier Transforms
by: Kalavasis, Alkis, et al.
Published: (2026)

(Im)possibility of Automated Hallucination Detection in Large Language Models
by: Karbasi, Amin, et al.
Published: (2025)

BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks
by: Li, Xinfu, et al.
Published: (2024)

Good-Enough LLM Obfuscation (GELO)
by: Belikov, Anatoly, et al.
Published: (2026)

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
by: Draguns, Andis, et al.
Published: (2024)

Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
by: Chow, Ka-Ho, et al.
Published: (2024)

Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
by: Wan, Guangnian, et al.
Published: (2026)

What is Learnable in Valiant's Theory of the Learnable?
by: Hanneke, Steve, et al.
Published: (2026)

Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
by: Cui, Xinyue, et al.
Published: (2025)