No article text was recorded for this version.
non-uniform safety alignment
Version 1 of 124 papers30 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient
- Blog: MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
- Blog: PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
- Blog: SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
- Blog: Perception-Guided Jailbreak Against Text-to-Image Models
- Blog: Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints
- Blog: CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models
- Blog: Geneshift: Impact of different scenario shift on Jailbreaking LLM
- Blog: BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs
- Blog: Disinformation Capabilities of Large Language Models
- Blog: AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories
- Blog: SafeEvalAgent: Toward Agentic and Self-Evolving Safety Evaluation of LLMs
- Blog: JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
- Blog: SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
- Blog: Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble
- Blog: SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
- Blog: MCP-SafetyBench: A Benchmark for Safety Evaluation of Large Language Models with Real-World MCP Servers
- Blog: DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization
- Blog: Towards Seed-Robust Safety Alignment in Text-to-Image Models
- Blog: EvilPromptFuzzer: generating inappropriate content based on text-to-image models
- Blog: Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges
- Blog: Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation
- Blog: Give LLMs a Security Course: Securing Retrieval-Augmented Code Generation via Knowledge Injection
- Blog: Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation
History & citation
Current · Permanent link
- This direction split from Automated Discovery of Model Specific Safety Vulnerabilities (67% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_uniform_safety_alignment_672e4e14,
title = {non-uniform safety alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-uniform-safety-alignment/rdr_672e4e1446674bf5b8e9cb12f3163cf6},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_non_uniform_safety_alignment_672e4e14_v1,
title = {non-uniform safety alignment},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-uniform-safety-alignment/rdr_672e4e1446674bf5b8e9cb12f3163cf6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}