Cover Image

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Garcia, Gabriel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language Cryptography and Security Performance I.2.6; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PoTS: Proof-of-Training-Steps for Backdoor Detection in Large Language Models
by: Seddik, Issam, et al.
Published: (2025)

Unlearning at Scale: Implementing the Right to be Forgotten in Large Language Models
by: X, Abdullah
Published: (2025)

Forget Attention: Importance-Aware Attention Is All You Need
by: Shin, Soohyeong, et al.
Published: (2026)

Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
by: Cotti, Luca, et al.
Published: (2025)

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models
by: Fadli, Samih
Published: (2025)

Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
by: Lelle, Travis
Published: (2026)

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It
by: Garcia, Gabriel
Published: (2026)

MEMSAD: Gradient-Coupled Anomaly Detection for Memory Poisoning in Retrieval-Augmented Agents
by: Gowda, Ishrith
Published: (2026)

EmoLoom-2B: Fast Base-Model Screening for Emotion Classification and VAD with Lexicon-Weak Supervision and KV-Off Evaluation
by: Li, Zilin, et al.
Published: (2026)

On the Limits of Learned Importance Scoring for KV Cache Compression
by: Steele, Brady
Published: (2026)

Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
by: Rosenblatt, Lucas, et al.
Published: (2026)

Attacking interpretable NLP systems
by: Abdukhamidov, Eldor, et al.
Published: (2025)

SALLIE: Safeguarding Against Latent Language & Image Exploits
by: Azov, Guy, et al.
Published: (2026)

Lightweight LLMs for Network Attack Detection in IoT Networks
by: Sudasinghe, Piyumi Bhagya, et al.
Published: (2026)

Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
by: Leonesi, Matteo, et al.
Published: (2026)

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
by: Shravan, Rohan
Published: (2026)

BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
by: DeLeeuw, Caleb
Published: (2026)

Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs
by: Hill, Brennen, et al.
Published: (2025)

No Free Swap: Protocol-Dependent Layer Redundancy in Transformers
by: Garcia, Gabriel
Published: (2026)

The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies
by: Garcia, Gabriel
Published: (2026)

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
by: Chauhan, Anay, et al.
Published: (2026)

Monotonicity as an Architectural Bias for Robust Language Models
by: Cooper, Patrick, et al.
Published: (2026)

Quantization-Robust LLM Unlearning via Low-Rank Adaptation
by: Abitante, João Vitor Boer, et al.
Published: (2026)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
by: Dang, Kieu, et al.
Published: (2025)

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales
by: Salfati, Samuel
Published: (2026)

Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text
by: Zhou, Tianyang, et al.
Published: (2026)

The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
by: Liu, Ming
Published: (2026)

Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
by: Young, Richard J., et al.
Published: (2026)

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
by: Gu, Hao, et al.
Published: (2025)

HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
by: Garg, Aashna, et al.
Published: (2026)

Annotation Entropy Predicts Per-Example Learning Dynamics in LoRA Fine-Tuning
by: Steele, Brady
Published: (2026)

OCRR: A Benchmark for Online Correction Recovery under Distribution Shift
by: Grassi, Adrian
Published: (2026)

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility
by: Szilvasy, Gergely, et al.
Published: (2026)

Ouroboros: Dynamic Weight Generation for Recursive Transformers via Input-Conditioned LoRA Modulation
by: Jaber, Jaber, et al.
Published: (2026)

Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction
by: Walker, Nicholas
Published: (2024)

Neural Activation Patterns Across Language Model Architectures: A Comprehensive Analysis of Cognitive Task Performance
by: Naser-Moghadasi, Mahdi, et al.
Published: (2026)

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure
by: Mahmood, Syed Naveed, et al.
Published: (2026)

When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
by: Young, Richard J., et al.
Published: (2025)

Continuous-Depth Transformers with Learned Control Dynamics
by: Jemley, Peter
Published: (2026)

PersonalLLM: Tailoring LLMs to Individual Preferences
by: Zollo, Thomas P., et al.
Published: (2024)