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 11 of 14

501. ICML 2025Towards Black-Box Membership Inference Attack for Diffusion Models
502. ICML 2025Towards flexible perception with visual memory
503. ICML 2025Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models
504. ICML 2025TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models
505. ICML 2025Trustworthy Machine Learning through Data-Specific Indistinguishability
506. ICML 2025Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
507. ICML 2025Validating Mechanistic Interpretations: An Axiomatic Approach
508. ICML 2025Weak-to-Strong Jailbreaking on Large Language Models
509. ICML 2025What makes an Ensemble (Un) Interpretable?
510. ICML 2025Which Attention Heads Matter for In-Context Learning?
511. ICML 2025WMarkGPT: Watermarked Image Understanding via Multimodal Large Language Models
512. ICML 2025X-Hacking: The Threat of Misguided AutoML
513. NeurIPS 2025AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness
514. NeurIPS 2025Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
515. NeurIPS 2025Additive Models Explained: A Computational Complexity Approach
516. NeurIPS 2025Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
517. NeurIPS 2025Alignment of Large Language Models with Constrained Learning
518. NeurIPS 2025Analogy-based Multi-Turn Jailbreak against Large Language Models
519. NeurIPS 2025Backdoor Cleaning without External Guidance in MLLM Fine-tuning
520. NeurIPS 2025Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
521. NeurIPS 2025BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
522. NeurIPS 2025C-SafeGen: Certified Safe LLM Generation with Claim-Based Streaming Guardrails
523. NeurIPS 2025CHiQPM: Calibrated Hierarchical Interpretable Image Classification
524. NeurIPS 2025Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration
525. NeurIPS 2025Combining Cost Constrained Runtime Monitors for AI Safety
526. NeurIPS 2025Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models
527. NeurIPS 2025Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time
528. NeurIPS 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
529. NeurIPS 2025CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D
530. NeurIPS 2025Detecting High-Stakes Interactions with Activation Probes
531. NeurIPS 2025Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
532. NeurIPS 2025Direct Alignment with Heterogeneous Preferences
533. NeurIPS 2025Discovering Opinion Intervals from Conflicts in Signed Graphs
534. NeurIPS 2025Distillation Robustifies Unlearning
535. NeurIPS 2025Does Representation Guarantee Welfare?
536. NeurIPS 2025DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers
537. NeurIPS 2025Dynamic Risk Assessments for Offensive Cybersecurity Agents
538. NeurIPS 2025Erasing Conceptual Knowledge from Language Models
539. NeurIPS 2025ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space
540. NeurIPS 2025Fair Deepfake Detectors Can Generalize
541. NeurIPS 2025Fairshare Data Pricing via Data Valuation for Large Language Models
542. NeurIPS 2025Faithful Group Shapley Value
543. NeurIPS 2025FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
544. NeurIPS 2025Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
545. NeurIPS 2025From Black-box to Causal-box: Towards Building More Interpretable Models
546. NeurIPS 2025From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
547. NeurIPS 2025From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
548. NeurIPS 2025From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes
549. NeurIPS 2025Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
550. NeurIPS 2025GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

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.