Cover Image

BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	DeLeeuw, Caleb
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Cryptography and Security Machine Learning I.2.7; I.2.6; K.4.1
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
by: Bercovich, Ivan, et al.
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)

Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
by: Blanco-Justicia, Alberto, et al.
Published: (2024)

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

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

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

Harmful Terms and Where to Find Them: Measuring and Modeling Unfavorable Financial Terms and Conditions in Shopping Websites at Scale
by: Tsai, Elisa, et al.
Published: (2025)

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

Powerful Training-Free Membership Inference Against Autoregressive Language Models
by: Ilić, David, et al.
Published: (2026)

KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety
by: Panchal, Viraj, et al.
Published: (2026)

Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
by: Beltoft, Stine, et al.
Published: (2025)

Human Values in a Single Sentence: Moral Presence, Hierarchies, and Transformer Ensembles on the Schwartz Continuum
by: Yeste, Víctor, et al.
Published: (2026)

REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs
by: Cohen, Liran, et al.
Published: (2025)

AlignDP: Hybrid Differential Privacy with Rarity-Aware Protection for LLMs
by: Gaikwad, Madhava
Published: (2025)

LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
by: Lucas, Tom, et al.
Published: (2026)

CAMP: Cumulative Agentic Masking and Pruning for Privacy Protection in Multi-Turn LLM Conversations
by: Panjwani, Aman
Published: (2026)

Transforming Computer Security and Public Trust Through the Exploration of Fine-Tuning Large Language Models
by: Crumrine, Garrett, et al.
Published: (2024)

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

Whisper Leak: a side-channel attack on Large Language Models
by: McDonald, Geoff, et al.
Published: (2025)

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization
by: Gu, Yongtong, et al.
Published: (2026)

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption
by: Morales, Jaime, et al.
Published: (2026)

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

Toward Secure and Compliant AI: Organizational Standards and Protocols for NLP Model Lifecycle Management
by: Arora, Sunil, et al.
Published: (2025)

Auditing Preferences for Brands and Cultures in LLMs
by: Rienecker, Jasmine, et al.
Published: (2026)

Predicting Known Vulnerabilities from Attack Descriptions Using Sentence Transformers
by: Othman, Refat
Published: (2026)

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

Scalable and Verifiable Federated Learning for Cross-Institution Financial Fraud Detection
by: Panth, Prajwal, et al.
Published: (2026)

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction
by: Garcia, Gabriel
Published: (2026)

How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
by: Wang, Yanshu, et al.
Published: (2026)

Retrieval Augmented Classification for Confidential Documents
by: Chang, Yeseul E., et al.
Published: (2026)

On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection
by: Schappacher-Tilp, Gudrun, et al.
Published: (2026)

Physics-R1: An Audited Olympiad Corpus and Recipe for Visual Physics Reasoning
by: Yang, Shan
Published: (2026)

More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
by: Yeste, Víctor, et al.
Published: (2026)

Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration
by: Yeste, Víctor, et al.
Published: (2026)

Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
by: Ye, Hua, et al.
Published: (2025)

Measuring Harmfulness of Computer-Using Agents
by: Tian, Aaron Xuxiang, et al.
Published: (2025)

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
by: Chen, Renmiao, et al.
Published: (2025)

Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
by: Oh, Myung Gyo, et al.
Published: (2024)