Cover Image

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bose, Avinandan, Lessard, Laurent, Fazel, Maryam, Dvijotham, Krishnamurthy Dj
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Offline Multi-task Transfer RL with Representational Penalization
by: Bose, Avinandan, et al.
Published: (2024)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
by: Shpilevskiy, Frederick, et al.
Published: (2025)

Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
by: Bose, Avinandan, et al.
Published: (2024)

LoRe: Personalizing LLMs via Low-Rank Reward Modeling
by: Bose, Avinandan, et al.
Published: (2025)

Efficient Error Certification for Physics-Informed Neural Networks
by: Eiras, Francisco, et al.
Published: (2023)

Protecting against simultaneous data poisoning attacks
by: Alex, Neel, et al.
Published: (2024)

Initializing Services in Interactive ML Systems for Diverse Users
by: Bose, Avinandan, et al.
Published: (2023)

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution
by: Kim, Minbeom, et al.
Published: (2026)

Achieving the Tightest Relaxation of Sigmoids for Formal Verification
by: Chevalier, Samuel, et al.
Published: (2024)

Norm-Bounded Low-Rank Adaptation
by: Wang, Ruigang, et al.
Published: (2025)

Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks
by: Wang, Ruigang, et al.
Published: (2024)

Provably effective detection of effective data poisoning attacks
by: Gallagher, Jonathan, et al.
Published: (2025)

Cold-Start Personalization via Training-Free Priors from Structured World Models
by: Bose, Avinandan, et al.
Published: (2026)

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
by: Boisvert, Léo, et al.
Published: (2025)

Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback
by: Zhou, Runlong, et al.
Published: (2025)

Dual Approximation Policy Optimization
by: Xiong, Zhihan, et al.
Published: (2024)

Large Language Models Can Verbatim Reproduce Long Malicious Sequences
by: Lin, Sharon, et al.
Published: (2025)

Provably Bounding Neural Network Preimages
by: Kotha, Suhas, et al.
Published: (2023)

Local linear convergence of gradient methods for overparameterized Gaussian mixtures
by: Wang, Jingxing, et al.
Published: (2026)

Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models
by: Xu, Weihang, et al.
Published: (2024)

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
by: Brown, Gavin, et al.
Published: (2024)

Verified Neural Compressed Sensing
by: Bunel, Rudy, et al.
Published: (2024)

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures
by: Zhou, Mo, et al.
Published: (2025)

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
by: Kim, Kyuyoung, et al.
Published: (2024)

Emergent specialization from participation dynamics and multi-learner retraining
by: Dean, Sarah, et al.
Published: (2022)

First line of defense: A robust first layer mitigates adversarial attacks
by: Suresh, Janani, et al.
Published: (2024)

Certified geometric robustness -- Super-DeepG
by: Cohen, Noémie, et al.
Published: (2026)

On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits
by: Maynard-Zhang, Leo, et al.
Published: (2026)

Evaluating lightweight unsupervised online IDS for masquerade attacks in CAN
by: Moriano, Pablo, et al.
Published: (2024)

Expressive Losses for Verified Robustness via Convex Combinations
by: De Palma, Alessandro, et al.
Published: (2023)

Learning to Receive Help: Intervention-Aware Concept Embedding Models
by: Zarlenga, Mateo Espinosa, et al.
Published: (2023)

Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models
by: Zhu, Libin, et al.
Published: (2026)

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
by: Choudhary, Sarthak, et al.
Published: (2025)

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
by: Chen, Shulun, et al.
Published: (2025)

Unregularized Linear Convergence in Zero-Sum Game from Preference Feedback
by: Chen, Shulun, et al.
Published: (2025)

A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
by: Xiong, Zhihan, et al.
Published: (2023)

The poison of dimensionality
by: Hoang, Lê-Nguyên
Published: (2024)

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

Adaptive Backtracking Line Search
by: Cavalcanti, Joao V., et al.
Published: (2024)

Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing
by: Narang, Adhyyan, et al.
Published: (2026)