Image de couverture de livre

Mind the Gap: A Practical Attack on GGUF Quantization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Egashira, Kazuki, Staab, Robin, Vero, Mark, He, Jingxuan, Vechev, Martin
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploiting LLM Quantization
par: Egashira, Kazuki, et autres
Publié: (2024)

Fewer Weights, More Problems: A Practical Attack on LLM Pruning
par: Egashira, Kazuki, et autres
Publié: (2025)

Watch your steps: Dormant Adversarial Behaviors that Activate upon LLM Finetuning
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation
par: De Muri, Giovanni, et autres
Publié: (2025)

Widening the Gap: Exploiting LLM Quantization via Outlier Injection
par: Zhan, Xiaohua, et autres
Publié: (2026)

Instruction Tuning for Secure Code Generation
par: He, Jingxuan, et autres
Publié: (2024)

Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark
par: Gloaguen, Thibaud, et autres
Publié: (2026)

Watermark Stealing in Large Language Models
par: Jovanović, Nikola, et autres
Publié: (2024)

A Unified Framework for LLM Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2026)

Watermarking Diffusion Language Models
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Discovering Spoofing Attempts on Language Model Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2024)

Ward: Provable RAG Dataset Inference via LLM Watermarks
par: Jovanović, Nikola, et autres
Publié: (2024)

Large Language Models are Advanced Anonymizers
par: Staab, Robin, et autres
Publié: (2024)

BaxBench: Can LLMs Generate Correct and Secure Backends?
par: Vero, Mark, et autres
Publié: (2025)

Black-Box Adversarial Attacks on LLM-Based Code Completion
par: Jenko, Slobodan, et autres
Publié: (2024)

SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization
par: Wang, Hao, et autres
Publié: (2026)

Delay, Plateau, or Collapse: Evaluating the Impact of Systematic Verification Error on RLVR
par: Egashira, Kazuki, et autres
Publié: (2026)

AutoBaxBuilder: Bootstrapping Code Security Benchmarking
par: von Arx, Tobias, et autres
Publié: (2025)

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
par: Vero, Mark, et autres
Publié: (2026)

LLM Fingerprinting via Semantically Conditioned Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Towards Watermarking of Open-Source LLMs
par: Gloaguen, Thibaud, et autres
Publié: (2025)

Black-Box Detection of Language Model Watermarks
par: Gloaguen, Thibaud, et autres
Publié: (2024)

A Synthetic Dataset for Personal Attribute Inference
par: Yukhymenko, Hanna, et autres
Publié: (2024)

Mind the Gap: Mixtures of Gaussians in Approximate Differential Privacy
par: Liu, Huikang, et autres
Publié: (2026)

Large Language Models for Code: Security Hardening and Adversarial Testing
par: He, Jingxuan, et autres
Publié: (2023)

Beyond Memorization: Violating Privacy Via Inference with Large Language Models
par: Staab, Robin, et autres
Publié: (2023)

Mind the Gap: Missing Cyber Threat Coverage in NIDS Datasets for the Energy Sector
par: Tory, Adrita Rahman, et autres
Publié: (2025)

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection
par: Zeng, Qirun, et autres
Publié: (2025)

Verification of Bit-Flip Attacks against Quantized Neural Networks
par: Zhang, Yedi, et autres
Publié: (2025)

Private Attribute Inference from Images with Vision-Language Models
par: Tömekçe, Batuhan, et autres
Publié: (2024)

Back to the Drawing Board for Fair Representation Learning
par: Pouget, Angéline, et autres
Publié: (2024)

Evading Data Contamination Detection for Language Models is (too) Easy
par: Dekoninck, Jasper, et autres
Publié: (2024)

Practical Feasibility of Gradient Inversion Attacks in Federated Learning
par: Valadi, Viktor, et autres
Publié: (2025)

Quantized Delta Weight Is Safety Keeper
par: Liu, Yule, et autres
Publié: (2024)

SoK: Data Minimization in Machine Learning
par: Staab, Robin, et autres
Publié: (2025)

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
par: Wang, Zhun, et autres
Publié: (2026)

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
par: Wang, Zhun, et autres
Publié: (2025)

Membership Inference Attack with Partial Features
par: Wang, Xurun, et autres
Publié: (2025)

Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis
par: He, Zhipeng, et autres
Publié: (2024)

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
par: Zhang, Heyi, et autres
Publié: (2025)