Cover Image

Oblivious Defense in ML Models: Backdoor Removal without Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goldwasser, Shafi, Shafer, Jonathan, Vafa, Neekon, Vaikuntanathan, Vinod
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computational Complexity Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Symmetric Perceptrons, Number Partitioning and Lattices
by: Vafa, Neekon, et al.
Published: (2025)

Adaptive Robustness of Hypergrid Johnson-Lindenstrauss
by: Bogdanov, Andrej, et al.
Published: (2025)

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning
by: Gluch, Greg, et al.
Published: (2025)

Near-Optimal Time-Sparsity Trade-Offs for Solving Noisy Linear Equations
by: Bangachev, Kiril, et al.
Published: (2024)

Efficient Public Verification of Private ML via Regularization
by: Bell, Zoë Ruha, et al.
Published: (2025)

Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange
by: Vaikuntanathan, Vinod, et al.
Published: (2026)

Generalized and Unified Equivalences between Hardness and Pseudoentropy
by: Hu, Lunjia, et al.
Published: (2025)

Average-Case Complexity of Quantum Stabilizer Decoding
by: Khesin, Andrey Boris, et al.
Published: (2025)

Sparse Linear Regression and Lattice Problems
by: Gupte, Aparna, et al.
Published: (2024)

Second-Order Min-Max Optimization with Lazy Hessians
by: Chen, Lesi, et al.
Published: (2024)

Cryptographic Hardness of Score Estimation
by: Song, Min Jae
Published: (2024)

Noise-tolerant learnability of shallow quantum circuits from statistics and the cost of quantum pseudorandomness
by: Wadhwa, Chirag, et al.
Published: (2024)

Robustness Inspired Graph Backdoor Defense
by: Zhang, Zhiwei, et al.
Published: (2024)

Seal Your Backdoor with Variational Defense
by: Sabolić, Ivan, et al.
Published: (2025)

Data-centric NLP Backdoor Defense from the Lens of Memorization
by: Wang, Zhenting, et al.
Published: (2024)

Quantization Blindspots: How Model Compression Breaks Backdoor Defenses
by: Pandey, Rohan, et al.
Published: (2025)

Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning
by: Golowich, Noah, et al.
Published: (2024)

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
by: Dvijotham, Krishnamurthy, et al.
Published: (2024)

Privately Estimating Black-Box Statistics
by: Steinke, Günter F., et al.
Published: (2025)

InstaHide's Sample Complexity When Mixing Two Private Images
by: Huang, Baihe, et al.
Published: (2020)

Backdoor Defense through Self-Supervised and Generative Learning
by: Sabolić, Ivan, et al.
Published: (2024)

Models That Prove Their Own Correctness
by: Amit, Noga, et al.
Published: (2024)

On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
by: Pichler, Georg, et al.
Published: (2024)

TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
by: Dai, Yanbo, et al.
Published: (2025)

Verifiable Quantum Advantage without Structure
by: Yamakawa, Takashi, et al.
Published: (2022)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
by: Zhang, Yuhao, et al.
Published: (2023)

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
by: Zeng, Rui, et al.
Published: (2024)

Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
by: Pan, Mengting, et al.
Published: (2026)

A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
by: elShehaby, Mohamed, et al.
Published: (2026)

Quantum-Computable One-Way Functions without One-Way Functions
by: Kretschmer, William, et al.
Published: (2024)

Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
by: Iwahana, Kazuki, et al.
Published: (2025)

DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
by: You, Ziyang, et al.
Published: (2026)

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
by: Ma, Hua, et al.
Published: (2023)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
by: Yan, Xinhai, et al.
Published: (2025)

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses
by: Pawlak, Stanisław, et al.
Published: (2025)

SteganoBackdoor: Stealthy and Data-Efficient Backdoor Attacks on Language Models
by: Xue, Eric, et al.
Published: (2025)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
by: Liu, Qin, et al.
Published: (2023)

Combining Machine Learning Defenses without Conflicts
by: Duddu, Vasisht, et al.
Published: (2024)

SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
by: Rieger, Phillip, et al.
Published: (2025)