A narrative survey that catalogs fifty papers on diffusion-based adversarial techniques across text, vision, and vision-language models, proposes a six-class taxonomy of diffusion roles plus a unified five-dimension evaluation framework, and releases a companion catalog.
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems
5 Pith papers cite this work, alongside 13 external citations. Polarity classification is still indexing.
5
Pith papers citing it
13
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.
SafeCtrl-RL frames LLM dialogue as a sequential decision process and uses an RL agent to iteratively refine prompts for safety at inference time.
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.
citing papers explorer
-
Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models
A narrative survey that catalogs fifty papers on diffusion-based adversarial techniques across text, vision, and vision-language models, proposes a six-class taxonomy of diffusion roles plus a unified five-dimension evaluation framework, and releases a companion catalog.
-
PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
PERSA combines RLHF with selective parameter-efficient updates to top transformer layers, raising style alignment scores from 35% to 96% on code feedback benchmarks while holding correctness near 100%.
-
SafeCtrl-RL: Inference-Time Adaptive Behaviour Control for LLM Dialogue via RL-Driven Prompt Optimisation
SafeCtrl-RL frames LLM dialogue as a sequential decision process and uses an RL agent to iteratively refine prompts for safety at inference time.
-
AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
The paper introduces a taxonomy of AI safety for LLMs organized into Trustworthy AI, Responsible AI, and Safe AI perspectives, accompanied by a review of state-of-the-art methods, challenges, and future directions.
-
LLM Harms: A Taxonomy and Discussion
Proposes a five-bucket taxonomy of LLM harms and calls for dynamic auditing, but the systematic review behind it is not reproducible and contains mismatched citations.