Social aspects · safety papers, 2023–2026

Key findings

• Social aspects · safety went from 4 papers in 2023 to 370 in 2026, roughly 93x in three years.
• ICML publishes the most Social aspects · safety work: 364 papers from 2023 to 2026, 53% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 0 in 2023 to 137 in 2026.
• Among the 5 topics under Alignment and Responsible AI, it ranks #3 by 2026 paper count; the fastest grower in the group, Social aspects · privacy, is up 6.6x versus 93x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026BarrierSteer: LLM Safety via Learning Barrier Steering
• ICML 2026Anti-Backdoor Coreset Selection via Cumulative Entropy
• ICLR 2026Bi-Criteria Metric Distortion
• CVPR 2026Omni-MMSI Toward Identity-attributed Social Interaction Understanding
• NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
• ICML 2025$S^2$FGL: Spatial Spectral Federated Graph Learning
• ICLR 2025The Hidden Cost of Waiting for Accurate Predictions
• CVPR 2025Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
• NeurIPS 2024Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
• ICML 2024Optimally Improving Cooperative Learning in a Social Setting
• ICLR 2024The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
• CVPR 2024Digital Life Project: Autonomous 3D Characters with Social Intelligence
• NeurIPS 2023Strategyproof Voting under Correlated Beliefs
• ICML 2023Adaptive Coordination in Social Embodied Rearrangement
• NeurIPS 2026Beyond Feature Disruption: Boundary-Diverting Unlearnable Examples against Linear Probing
• ICML 2026AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
• ICLR 2026PRISON: Unmasking the Criminal Potential of Large Language Models
• CVPR 2026Spot The Ball A Benchmark for Visual Social Inference
• NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
• ICML 2025Adversaries Can Misuse Combinations of Safe Models

All Social aspects · safety papers

277 papers, page 5 of 6

201. NeurIPS 2025Representational Difference Explanations
202. NeurIPS 2025Residual Stream Analysis of Overfitting And Structural Disruptions
203. NeurIPS 2025RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
204. NeurIPS 2025Risk Management for Mitigating Benchmark Failure Modes: BenchRisk
205. NeurIPS 2025Robust Explanations of Graph Neural Networks via Graph Curvatures
206. NeurIPS 2025Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
207. NeurIPS 2025SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
208. NeurIPS 2025Safety Depth in Large Language Models: A Markov Chain Perspective
209. NeurIPS 2025Safety Pretraining: Toward the Next Generation of Safe AI
210. NeurIPS 2025SafeVid: Toward Safety Aligned Video Large Multimodal Models
211. NeurIPS 2025SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
212. NeurIPS 2025SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
213. NeurIPS 2025Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions
214. NeurIPS 2025Scalable Fingerprinting of Large Language Models
215. NeurIPS 2025Scalable Valuation of Human Feedback through Provably Robust Model Alignment
216. NeurIPS 2025Scaling Laws For Scalable Oversight
217. NeurIPS 2025Semantic Representation Attack against Aligned Large Language Models
218. NeurIPS 2025SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism
219. NeurIPS 2025SHAP values via sparse Fourier representation
220. NeurIPS 2025SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
221. NeurIPS 2025Shape it Up! Restoring LLM Safety during Finetuning
222. NeurIPS 2025Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
223. NeurIPS 2025SpEx: A Spectral Approach to Explainable Clustering
224. NeurIPS 2025Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
225. NeurIPS 2025STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
226. NeurIPS 2025StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models
227. NeurIPS 2025Strategic Classification with Non-Linear Classifiers
228. NeurIPS 2025Strategic Cost Selection in Participatory Budgeting
229. NeurIPS 2025Strategic Hypothesis Testing
230. NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
231. NeurIPS 2025Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
232. NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
233. NeurIPS 2025The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
234. NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
235. NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
236. NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
237. NeurIPS 2025Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
238. NeurIPS 2025Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
239. NeurIPS 2025Unlearning-Aware Minimization
240. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
241. NeurIPS 2025Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization
242. NeurIPS 2025Vector Database Watermarking
243. NeurIPS 2025Versatile Transferable Unlearnable Example Generator
244. NeurIPS 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
245. NeurIPS 2025Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
246. NeurIPS 2025VLMs can Aggregate Scattered Training Patches
247. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
248. NeurIPS 2025What Really is a Member? Discrediting Membership Inference via Poisoning
249. NeurIPS 2025Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
250. NeurIPS 2025Why Do Some Language Models Fake Alignment While Others Don't?

FAQ

How many Social aspects · safety papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

688 in total: 4 in 2023, 41 in 2024, 273 in 2025, 370 in 2026.

How many Social aspects · safety papers are at NeurIPS 2026?

NeurIPS 2026 has 121 Social aspects · safety papers, versus 131 the year before.

How many Social aspects · safety papers are at ICLR 2026?

ICLR 2026 has 20 Social aspects · safety papers, versus 11 the year before.

How many Social aspects · safety papers are at ICML 2026?

ICML 2026 has 226 Social aspects · safety papers, versus 130 the year before.

How many Social aspects · safety papers are at CVPR 2026?

CVPR 2026 has 3 Social aspects · safety papers, versus 1 the year before.

Which conference publishes the most Social aspects · safety papers?

ICML, with 364 papers from 2023 to 2026.