Cover Image

AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khanna, Danush, Kumar, Gurucharan Marthi Krishna, Ghosh, Basab, Narsupalli, Yaswanth, Jain, Vinija, Sharma, Vasu, Chadha, Aman, Das, Amitava
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
by: Das, Amitava, et al.
Published: (2025)

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment
by: Das, Amitava, et al.
Published: (2025)

RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence
by: Rawte, Vipula, et al.
Published: (2025)

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

HAMLOCK: HArdware-Model LOgically Combined attacK
by: Amgain, Sanskar, et al.
Published: (2025)

TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
by: Das, Amitava, et al.
Published: (2025)

MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation
by: Kumar, Gurucharan Marthi Krishna, et al.
Published: (2024)

AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
by: Das, Amitava, et al.
Published: (2025)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
by: Sahoo, Subramanyam, et al.
Published: (2026)

Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
by: Dixit, Shreyas, et al.
Published: (2025)

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization
by: Khanna, Danush, et al.
Published: (2025)

D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space
by: Raina, Samarth, et al.
Published: (2025)

AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
by: Roy, Aniruddha, et al.
Published: (2025)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
by: Saha, Anusa, et al.
Published: (2026)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
by: Wanaskar, Kapil, et al.
Published: (2026)

LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs
by: Sidibomma, Rushendra, et al.
Published: (2024)

MAAT: Multi-phase Adapter-Aware Targeted Unlearning
by: Yagnik, Suryash, et al.
Published: (2026)

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
by: Sinha, Neelabh, et al.
Published: (2024)

Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
by: Sinha, Neelabh, et al.
Published: (2024)

NestedMorph: Enhancing Deformable Medical Image Registration with Nested Attention Mechanisms
by: Kumar, Gurucharan Marthi Krishna, et al.
Published: (2024)

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations
by: Borah, Abhilekh, et al.
Published: (2025)

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
by: Das, Arion, et al.
Published: (2026)

PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
by: Kumar, Harsh, et al.
Published: (2026)

The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
by: Barman, Niyar R, et al.
Published: (2024)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
by: Sahoo, Subramanyam, et al.
Published: (2026)

Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
by: Kasat, Aryan, et al.
Published: (2026)

Dial E for Ethical Enforcement: institutional VETO power as a governance primitive
by: Sahoo, Subramanyam, et al.
Published: (2026)

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
by: Sahoo, Subramanyam, et al.
Published: (2026)

Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models
by: Singh, Smriti, et al.
Published: (2024)

I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
by: Sahoo, Subramanyam, et al.
Published: (2026)

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
by: Sahoo, Subramanyam, et al.
Published: (2025)

Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
by: Vats, Arpita, et al.
Published: (2024)

On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models
by: Wijesiriwardene, Thilini, et al.
Published: (2023)

The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey
by: Pawar, Saurav, et al.
Published: (2024)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
by: Saha, Partha Pratim, et al.
Published: (2026)

ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models
by: Narsupalli, Yaswanth, et al.
Published: (2024)

AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
by: Mukhopadhyay, Snehasis, et al.
Published: (2025)

KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
by: Wijesiriwardene, Thilini, et al.
Published: (2024)

SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
by: Rani, Anku, et al.
Published: (2023)

How Culturally Aware are Vision-Language Models?
by: Burda-Lassen, Olena, et al.
Published: (2024)