Cover Image

Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mamun, Md Abdullah Al, Alouani, Ihsen, Abu-Ghazaleh, Nael
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Privacy in Federated Learning with Spiking Neural Networks
by: Aksu, Dogukan, et al.
Published: (2025)

GPUVM: GPU-driven Unified Virtual Memory
by: Nazaraliyev, Nurlan, et al.
Published: (2024)

Balanced and Elastic End-to-end Training of Dynamic LLMs
by: Wahib, Mohamed, et al.
Published: (2025)

From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation
by: Bantel, Linus, et al.
Published: (2026)

Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation
by: Feng, Weiqi, et al.
Published: (2024)

Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection
by: Venkatesha, Yeshwanth, et al.
Published: (2025)

Regulating Branch Parallelism in LLM Serving
by: Gandhi, Swapnil, et al.
Published: (2026)

GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems
by: Wawdhane, Sourish, et al.
Published: (2026)

Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
by: Kodavanti, Sravanth, et al.
Published: (2026)

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
by: Ma, Qianli, et al.
Published: (2025)

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
by: Cho, Minsik, et al.
Published: (2024)

Glia: A Human-Inspired AI for Automated Systems Design and Optimization
by: Hamadanian, Pouya, et al.
Published: (2025)

Elevating Semantic Exploration: A Novel Approach Utilizing Distributed Repositories
by: Bellandi, Valerio
Published: (2025)

Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design
by: Anthony, Quentin, et al.
Published: (2025)

FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
by: Li, Weiqing, et al.
Published: (2025)

LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems
by: Li, Yufei, et al.
Published: (2025)

FedSEA-LLaMA: A Secure, Efficient and Adaptive Federated Splitting Framework for Large Language Models
by: Zhang, Zishuai, et al.
Published: (2025)

Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction
by: Xia, Menglin, et al.
Published: (2023)

Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks
by: Chandrasekar, Ashok, et al.
Published: (2026)

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
by: Wang, Jinheng, et al.
Published: (2025)

MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment
by: Li, Yufei, et al.
Published: (2025)

A Structure-Agnostic Co-Tuning Framework for LLMs and SLMs in Cloud-Edge Systems
by: Liu, Yuze, et al.
Published: (2025)

EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model
by: Pinnock, Alyssa, et al.
Published: (2025)

Characterizing Performance-Energy Trade-offs of Large Language Models in Multi-Request Workflows
by: Ifath, Md. Monzurul Amin, et al.
Published: (2026)

An Evaluation of LLMs Inference on Popular Single-board Computers
by: Tung, et al.
Published: (2025)

ELANA: A Simple Energy and Latency Analyzer for LLMs
by: Chiang, Hung-Yueh, et al.
Published: (2025)

Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs
by: Xin, Jihao, et al.
Published: (2026)

Training LLMs with Fault Tolerant HSDP on 100,000 GPUs
by: Salpekar, Omkar, et al.
Published: (2026)

SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization
by: Tschand, Arya, et al.
Published: (2025)

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
by: Yang, Ningyuan, et al.
Published: (2025)

A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering
by: Dhar, Nobel, et al.
Published: (2025)

Tesserae: Scalable Placement Policies for Deep Learning Workloads
by: Bian, Song, et al.
Published: (2025)

Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges
by: Islam, Md Romyull, et al.
Published: (2025)

FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs
by: Zhang, Haijun, et al.
Published: (2025)

PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications
by: Mell, Stephen, et al.
Published: (2026)

Pact: A Choreographic Language for Agentic Ecosystems
by: Gopinathan, Kiran, et al.
Published: (2026)

ARGUS: Agentic GPU Optimization Guided by Data-Flow Invariants
by: Mai, Haohui, et al.
Published: (2026)

Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation
by: Fu, Kairui, et al.
Published: (2025)

DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs
by: Hu, Ziyu, et al.
Published: (2025)

Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes
by: Dearing, Matthew T., et al.
Published: (2025)