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

688 papers, page 4 of 14

151. ICML 2026OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
152. ICML 2026Optimal Regularization for Performative Learning
153. ICML 2026Optimal Transport Group Counterfactual Explanations
154. ICML 2026Orthogonal Concept Erasure for Diffusion Models
155. ICML 2026OSCS: Online Selection with Provable FAR Control for LLM Safety
156. ICML 2026Peer-Preservation in Frontier Models
157. ICML 2026PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
158. ICML 2026PlugGuard: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection
159. ICML 2026Pluralistic Leaderboards
160. ICML 2026Poison with Style: A Practical Poisoning Attack on Code Large Language Models
161. ICML 2026Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable
162. ICML 2026Pressure Reveals Character: Behavioural Alignment Evaluation at Depth
163. ICML 2026Proactive Defense Benchmark against Deepfake Generation
164. ICML 2026Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
165. ICML 2026Profiling the Irrational Agent: Cognitive Modeling of LLM Behaviors in Sequential Jailbreaks
166. ICML 2026Prompt Injection as Role Confusion
167. ICML 2026Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
168. ICML 2026Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment
169. ICML 2026Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
170. ICML 2026Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better
171. ICML 2026REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
172. ICML 2026Reasoning Models Struggle to Control their Chains of Thought
173. ICML 2026RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
174. ICML 2026Reflector: Internalizing Step-wise Reflection against Indirect Jailbreaks
175. ICML 2026Reverse-Engineering Model Editing on Language Models
176. ICML 2026Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
177. ICML 2026Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
178. ICML 2026Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
179. ICML 2026Robust AI Evaluation through Maximal Lotteries
180. ICML 2026Robust Human-AI Complementarity under Uncertainty
181. ICML 2026Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
182. ICML 2026SAEs-BrainMap: Unveiling the Emergence of Specialized Concepts in Deep Models via Brain Alignment
183. ICML 2026Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
184. ICML 2026SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
185. ICML 2026Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed
186. ICML 2026Safety-Efficacy Trade Off: Robustness against Data-Poisoning
187. ICML 2026Same Question, Different Lies: Cross-Context Consistency (C³) for Black-Box Sandbagging Detection
188. ICML 2026SARSteer: Safeguarding Large Audio Language Models via Safe-Ablated Refusal Steering
189. ICML 2026SecCodePRM: A Process Reward Model for Code Security
190. ICML 2026Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
191. ICML 2026Securing Multimodal AI through Internal Information Decomposition
192. ICML 2026Social Hippocampus Memory Learning
193. ICML 2026SOPE: Situation-Aware and Statistically Indistinguishable Privacy Exfiltration for MCP-enabled Agents
194. ICML 2026Sparse and Faithful Local Explanations with Piecewise Linear Surrogates
195. ICML 2026Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
196. ICML 2026Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs
197. ICML 2026Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
198. ICML 2026SpatialJB: How Text Distribution Art Becomes The "Jailbreak Key" for LLM Guardrails
199. ICML 2026Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
200. ICML 2026Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard

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.