Social aspects · safety papers, 2023–2026
Social aspect: safety
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 688 papers are tagged with this topic.
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.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 2 | 0 | 2 | 0 | 4 |
| 2024 | 23 | 11 | 6 | 1 | 41 |
| 2025 | 131 | 11 | 130 | 1 | 273 |
| 2026 | 121 | 20 | 226 | 3 | 370 |
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
273 papers, page 6 of 6
- NeurIPS 2025TAI3: Testing Agent Integrity in Interpreting User Intent
- NeurIPS 2025Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
- NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
- NeurIPS 2025The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction
- NeurIPS 2025The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
- NeurIPS 2025Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
- NeurIPS 2025Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons
- NeurIPS 2025Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
- NeurIPS 2025Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
- NeurIPS 2025Unlearning-Aware Minimization
- NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
- NeurIPS 2025Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization
- NeurIPS 2025Vector Database Watermarking
- NeurIPS 2025Versatile Transferable Unlearnable Example Generator
- NeurIPS 2025Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs
- NeurIPS 2025Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
- NeurIPS 2025VLMs can Aggregate Scattered Training Patches
- NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
- NeurIPS 2025What Really is a Member? Discrediting Membership Inference via Poisoning
- NeurIPS 2025Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models
- NeurIPS 2025Why Do Some Language Models Fake Alignment While Others Don't?
- NeurIPS 2025Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
- NeurIPS 2025World Models Should Prioritize the Unification of Physical and Social Dynamics
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Social aspects · safety papers grew at ICML from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "social-safety"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
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.