Buchumschlag

Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kharinaev, Artyom, Moskvoretskii, Viktor, Shvetsov, Egor, Studenikina, Kseniia, Mikhail, Bykov, Burnaev, Evgeny
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

EBES: Easy Benchmarking for Event Sequences
von: Osin, Dmitry, et al.
Veröffentlicht: (2024)

Investigating the Impact of Quantization on Adversarial Robustness
von: Li, Qun, et al.
Veröffentlicht: (2024)

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
von: Zhelnin, Maxim, et al.
Veröffentlicht: (2024)

Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security
von: Zhao, Wei, et al.
Veröffentlicht: (2025)

A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
von: Li, Jie, et al.
Veröffentlicht: (2024)

Protecting Private Code in IDE Autocomplete using Differential Privacy
von: Grigorenko, Evgeny, et al.
Veröffentlicht: (2026)

Safety Layers in Aligned Large Language Models: The Key to LLM Security
von: Li, Shen, et al.
Veröffentlicht: (2024)

Robustifying Safety-Aligned Large Language Models through Clean Data Curation
von: Liu, Xiaoqun, et al.
Veröffentlicht: (2024)

A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense
von: Zhai, Keke
Veröffentlicht: (2024)

Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency
von: Wickramasekara, Akila, et al.
Veröffentlicht: (2024)

Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
von: Wu, Jinman, et al.
Veröffentlicht: (2026)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
von: Chen, Yulong, et al.
Veröffentlicht: (2025)

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
von: Song, Weiming, et al.
Veröffentlicht: (2026)

USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
von: Zheng, Baolin, et al.
Veröffentlicht: (2025)

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
von: Wang, Xunguang, et al.
Veröffentlicht: (2026)

Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt
von: Gu, Yujie, et al.
Veröffentlicht: (2026)

On Jailbreaking Quantized Language Models Through Fault Injection Attacks
von: Zahran, Noureldin, et al.
Veröffentlicht: (2025)

Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models
von: Hossain, Elias, et al.
Veröffentlicht: (2025)

Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation
von: Wang, Haoyu, et al.
Veröffentlicht: (2024)

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
von: Huang, Tiansheng, et al.
Veröffentlicht: (2024)

FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations
von: Shuster, Shaun, et al.
Veröffentlicht: (2025)

Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries
von: Manuel, Dylan, et al.
Veröffentlicht: (2024)

On the Reliability and Stability of Selective Methods in Malware Classification Tasks
von: Herzog, Alexander, et al.
Veröffentlicht: (2025)

Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
von: Tan, Rui Yang, et al.
Veröffentlicht: (2026)

Understanding the Effects of Safety Unalignment on Large Language Models
von: Halloran, John T.
Veröffentlicht: (2026)

Internal Safety Collapse in Frontier Large Language Models
von: Wu, Yutao, et al.
Veröffentlicht: (2026)

Quantized Delta Weight Is Safety Keeper
von: Liu, Yule, et al.
Veröffentlicht: (2024)

DrLLM: Prompt-Enhanced Distributed Denial-of-Service Resistance Method with Large Language Models
von: Yin, Zhenyu, et al.
Veröffentlicht: (2024)

Finetuning Large Language Models for Vulnerability Detection
von: Shestov, Alexey, et al.
Veröffentlicht: (2024)

Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models
von: Biskupski, Tom, et al.
Veröffentlicht: (2026)

Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation
von: Zhang, Wenhui, et al.
Veröffentlicht: (2025)

SGuard-v1: Safety Guardrail for Large Language Models
von: Lee, JoonHo, et al.
Veröffentlicht: (2025)

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
von: David, Isaac, et al.
Veröffentlicht: (2026)

State-Dependent Safety Failures in Multi-Turn Language Model Interaction
von: Li, Pengcheng, et al.
Veröffentlicht: (2026)

(Security) Assertions by Large Language Models
von: Kande, Rahul, et al.
Veröffentlicht: (2023)

LLMmap: Fingerprinting For Large Language Models
von: Pasquini, Dario, et al.
Veröffentlicht: (2024)

Backdooring Bias in Large Language Models
von: Das, Anudeep, et al.
Veröffentlicht: (2026)

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models
von: Owiredu-Ashley, Harry
Veröffentlicht: (2026)

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
von: Zeng, Yi, et al.
Veröffentlicht: (2024)

Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models
von: Luo, Huaiying, et al.
Veröffentlicht: (2025)