Cover Image

Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ferrand, Jean-Charles Noirot, Beugin, Yohan, Pauley, Eric, Sheatsley, Ryan, McDaniel, Patrick
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
by: Domico, Kyle, et al.
Published: (2025)

Characterizing the Modification Space of Signature IDS Rules
by: Guide, Ryan, et al.
Published: (2024)

Longitudinal Analyses of SAST Tools: A CodeQL Case Study
by: Ferrand, Jean-Charles Noirot, et al.
Published: (2026)

Efficient Storage Integrity in Adversarial Settings
by: Burke, Quinn, et al.
Published: (2025)

Secure IP Address Allocation at Cloud Scale
by: Pauley, Eric, et al.
Published: (2022)

ParTEETor: A System for Partial Deployments of TEEs within Tor
by: King, Rachel, et al.
Published: (2024)

LibIHT: A Hardware-Based Approach to Efficient and Evasion-Resistant Dynamic Binary Analysis
by: Zhao, Changyu, et al.
Published: (2025)

A Public and Reproducible Assessment of the Topics API on Real Data
by: Beugin, Yohan, et al.
Published: (2024)

Technical Report: The Need for a (Research) Sandstorm through the Privacy Sandbox
by: Beugin, Yohan, et al.
Published: (2025)

The Role of Learning in Attacking ML-based Network Intrusion Detection
by: Domico, Kyle, et al.
Published: (2026)

Securing Cloud File Systems with Trusted Execution
by: Burke, Quinn, et al.
Published: (2023)

On the Robustness Tradeoff in Fine-Tuning
by: Li, Kunyang, et al.
Published: (2025)

Err on the Side of Texture: Texture Bias on Real Data
by: Hoak, Blaine, et al.
Published: (2024)

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
by: Li, MingSheng, et al.
Published: (2025)

On Scalable Integrity Checking for Secure Cloud Disks
by: Burke, Quinn, et al.
Published: (2024)

A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
by: Wu, Fangzhou, et al.
Published: (2024)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
by: Zhang, Jiawen, et al.
Published: (2025)

MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
by: Guo, Weiyang, et al.
Published: (2025)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
by: Zhang, Yi, et al.
Published: (2025)

Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
by: Kim, Jaehan, et al.
Published: (2025)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
by: Andriushchenko, Maksym, et al.
Published: (2024)

Reimagining Safety Alignment with An Image
by: Xia, Yifan, et al.
Published: (2025)

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment
by: Kuznetsov, Daniel, et al.
Published: (2026)

Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference
by: Yang, Fan
Published: (2026)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
by: Li, Hao, et al.
Published: (2026)

Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
by: Chen, Yu, et al.
Published: (2026)

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
by: Liu, Xiaogeng, et al.
Published: (2024)

Agent Safety Alignment via Reinforcement Learning
by: Sha, Zeyang, et al.
Published: (2025)

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

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, et al.
Published: (2025)

Measuring Safety Alignment Effects in Autonomous Security Agents
by: David, Isaac, et al.
Published: (2026)

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

Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
by: Luo, Weidi, et al.
Published: (2025)

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

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
by: Vega, Jason, et al.
Published: (2025)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
by: Campbell, David, et al.
Published: (2026)

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
by: Li, Nanxi, et al.
Published: (2025)

MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
by: Yan, Lu, et al.
Published: (2025)

On The Dangers of Poisoned LLMs In Security Automation
by: Karlsen, Patrick, et al.
Published: (2025)

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?
by: Yin, Qingyu, et al.
Published: (2025)