Copertina

Tamper-Resistant Safeguards for Open-Weight LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tamirisa, Rishub, Bharathi, Bhrugu, Phan, Long, Zhou, Andy, Gatti, Alice, Suresh, Tarun, Lin, Maxwell, Wang, Justin, Wang, Rowan, Arel, Ron, Zou, Andy, Song, Dawn, Li, Bo, Hendrycks, Dan, Mazeika, Mantas
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FedSelect: Customized Selection of Parameters for Fine-Tuning during Personalized Federated Learning
di: Tamirisa, Rishub, et al.
Pubblicazione: (2023)

TextQuests: How Good are LLMs at Text-Based Video Games?
di: Phan, Long, et al.
Pubblicazione: (2025)

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
di: Tamirisa, Rishub, et al.
Pubblicazione: (2024)

Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search
di: Zhou, Andy, et al.
Pubblicazione: (2025)

Aggressive Compression Enables LLM Weight Theft
di: Brown, Davis, et al.
Pubblicazione: (2026)

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
di: Mazeika, Mantas, et al.
Pubblicazione: (2025)

Improving Alignment and Robustness with Circuit Breakers
di: Zou, Andy, et al.
Pubblicazione: (2024)

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
di: Mazeika, Mantas, et al.
Pubblicazione: (2024)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
di: Ren, Richard, et al.
Pubblicazione: (2024)

Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
di: O'Brien, Kyle, et al.
Pubblicazione: (2025)

Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
di: Wei, Boyi, et al.
Pubblicazione: (2025)

Representation Engineering: A Top-Down Approach to AI Transparency
di: Zou, Andy, et al.
Pubblicazione: (2023)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2025)

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
di: Ren, Richard, et al.
Pubblicazione: (2025)

MITS-GAN: Safeguarding Medical Imaging from Tampering with Generative Adversarial Networks
di: Pasqualino, Giovanni, et al.
Pubblicazione: (2024)

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
di: Li, Nathaniel, et al.
Pubblicazione: (2024)

A Composition Theorem for Binomially Weighted Averages
di: Liu, Andy, et al.
Pubblicazione: (2026)

Reducing Political Manipulation with Consistency Training
di: Phan, Long, et al.
Pubblicazione: (2026)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
di: Andriushchenko, Maksym, et al.
Pubblicazione: (2024)

Design Principles for the Information Architecture of a SMET Education Digital Library.
di: Dong, Andy, et al.
Pubblicazione: (2001)

VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval
di: Ye, Huayuan, et al.
Pubblicazione: (2025)

Introduction to AI Safety, Ethics, and Society
di: Hendrycks, Dan
Pubblicazione: (2024)

Introduction to AI Safety, Ethics, and Society
di: Hendrycks, Dan
Pubblicazione: (2024)

Navigating Consumer Resistance: A Bibliometric Analysis of Innovation Resistance Theory and Future Research Directions
di: Tarun, Mehta
Pubblicazione: (2026)

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
di: Wang, Boxin, et al.
Pubblicazione: (2023)

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs
di: Sanyal, Debdeep, et al.
Pubblicazione: (2025)

Extensions of Real-Weighted Fractional Arboricity
di: Moxley, Rowan
Pubblicazione: (2025)

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection
di: Phan, Hoang, et al.
Pubblicazione: (2025)

D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
di: Krishna, Satyapriya, et al.
Pubblicazione: (2025)

Enhancing Biosecurity in Tamper-Resistant Large Language Models With Quantum Gradient Descent
di: Hai, Fahmida, et al.
Pubblicazione: (2025)

Superintelligence Strategy: Expert Version
di: Hendrycks, Dan, et al.
Pubblicazione: (2025)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
di: Qi, Xiangyu, et al.
Pubblicazione: (2024)

Excursion – Marine Ecology Point Dagger, Torquay
di: Arnold, Andy
Pubblicazione: (2018)

Migratory Capers in my Garden
di: Arnold, Andy
Pubblicazione: (2020)

Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation
di: Gray, Andy
Pubblicazione: (2026)

Epistemic Closure and the Irreversibility of Misalignment: Modeling Systemic Barriers to Alignment Innovation
di: Williams, Andy
Pubblicazione: (2025)

The AI Codebase Maturity Model: From Assisted Coding to Fully Autonomous Systems
di: Anderson, Andy
Pubblicazione: (2026)

Ultracoproducts and weak containment for flows of topological groups
di: Zucker, Andy
Pubblicazione: (2024)

Reliability, validity, and path coefficient
di: Alfatih, Andy
Pubblicazione: (2025)

ACUTE EFFECTS OF VARYING ISOMETRIC MIDTHIGH PULL DURATIONS ON SUBSEQUENT SQUAT JUMP PERFORMANCE
di: Morales, Andy
Pubblicazione: (2025)