Copertina

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Labiad, Ismail, Videau, Mathurin, Kowalski, Matthieu, Schoenauer, Marc, Leite, Alessandro, Kempe, Julia, Teytaud, Olivier
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mixture of Experts in Image Classification: What's the Sweet Spot?
di: Videau, Mathurin, et al.
Pubblicazione: (2024)

Evolutionary Pre-Prompt Optimization for Mathematical Reasoning
di: Videau, Mathurin, et al.
Pubblicazione: (2024)

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
di: Bouaziz, Wassim, et al.
Pubblicazione: (2025)

Evolutionary Retrofitting
di: Videau, Mathurin, et al.
Pubblicazione: (2024)

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets
di: Videau, Mathurin, et al.
Pubblicazione: (2025)

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say
di: Zhang, Mingxuan, et al.
Pubblicazione: (2026)

Provably Robust and Secure Steganography in Asymmetric Resource Scenario
di: Bai, Minhao, et al.
Pubblicazione: (2024)

Efficient Byzantine-Robust and Provably Privacy-Preserving Federated Learning
di: Nie, Chenfei, et al.
Pubblicazione: (2024)

Provably Robust Multi-bit Watermarking for AI-generated Text
di: Qu, Wenjie, et al.
Pubblicazione: (2024)

STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
di: Qi, Yuang, et al.
Pubblicazione: (2026)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
di: Li, Jiate, et al.
Pubblicazione: (2025)

Provable Privacy Attacks on Trained Shallow Neural Networks
di: Smorodinsky, Guy, et al.
Pubblicazione: (2024)

Watermarking Autoregressive Image Generation
di: Jovanović, Nikola, et al.
Pubblicazione: (2025)

Robust Covert Quantum Communication under Bounded Channel Uncertainty
di: Arghavani, Abbas, et al.
Pubblicazione: (2026)

On Using Certified Training towards Empirical Robustness
di: De Palma, Alessandro, et al.
Pubblicazione: (2024)

Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards
di: Normann, Philipp, et al.
Pubblicazione: (2026)

CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization
di: Wang, Derui, et al.
Pubblicazione: (2025)

Provably Secure Steganography Based on List Decoding
di: Pang, Kaiyi, et al.
Pubblicazione: (2026)

Provable Execution in Real-Time Embedded Systems
di: Neto, Antonio Joia, et al.
Pubblicazione: (2025)

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
di: Zhang, Rui, et al.
Pubblicazione: (2026)

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

Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography
di: Zhu, Jiahao, et al.
Pubblicazione: (2024)

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

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
di: Shen, Zeyu, et al.
Pubblicazione: (2025)

Retraining with Predicted Hard Labels Provably Increases Model Accuracy
di: Das, Rudrajit, et al.
Pubblicazione: (2024)

Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security
di: Wang, Haodi, et al.
Pubblicazione: (2024)

Beyond Algorithmic Proofs: Towards Implementation-Level Provable Security
di: Shang, Jiahui, et al.
Pubblicazione: (2025)

Towards Provably Secure Generative AI: Reliable Consensus Sampling
di: Cui, Yu, et al.
Pubblicazione: (2025)

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
di: Saxena, Aman, et al.
Pubblicazione: (2026)

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
di: Schuchardt, Jan, et al.
Pubblicazione: (2023)

MULTISS: un protocole de stockage confidentiel {à} long terme sur plusieurs r{é}seaux QKD
di: Prévost, Thomas, et al.
Pubblicazione: (2025)

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data
di: Pu, Yuwen, et al.
Pubblicazione: (2024)

Full-Stack Knowledge Graph and LLM Framework for Post-Quantum Cyber Readiness
di: Erlemann, Rasmus, et al.
Pubblicazione: (2026)

Enhancing Smart Contract Vulnerability Detection in DApps Leveraging Fine-Tuned LLM
di: Bu, Jiuyang, et al.
Pubblicazione: (2025)

Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments
di: Rigaki, Maria, et al.
Pubblicazione: (2024)

Asymmetric Mempool DoS Security: Formal Definitions and Provable Secure Designs
di: Ding, Wanning, et al.
Pubblicazione: (2024)

SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling
di: Wang, Yaofei, et al.
Pubblicazione: (2025)

Provably Secure Covert Messaging Using Image-based Diffusion Processes
di: Bauer, Luke A., et al.
Pubblicazione: (2025)

Provably Robust Watermarks for Open-Source Language Models
di: Christ, Miranda, et al.
Pubblicazione: (2024)

Provable Privacy Guarantee for Individual Identities and Locations in Large-Scale Contact Tracing
di: Nicewarner, Tyler, et al.
Pubblicazione: (2024)