Adversarial Robustness papers, 2023–2026

Key findings

• Adversarial Robustness went from 313 papers in 2023 to 317 in 2026, roughly 1.0x in three years.
• NeurIPS publishes the most Adversarial Robustness work: 422 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Alignment and Safety: papers tagged with both rose from 13 in 2023 to 56 in 2026.
• Among the 5 topics under Security and Trust, it ranks #1 by 2026 paper count; the fastest grower in the group, Watermarking, is up 9.3x versus 1.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Little Robustness Is All You Need: Leveraging Predictions for Contextual Optimization
• ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
• ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
• CVPR 2026A Combination of Noise and Bilateral Filters Achieve Supralinear and
• NeurIPS 2025A Unified Approach to Submodular Maximization Under Noise
• ICML 2025Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian
• ICLR 2025$\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples
• CVPR 2025A Unified, Resilient, and Explainable Adversarial Patch Detector
• NeurIPS 2024A StrongREJECT for Empty Jailbreaks
• ICML 2024Adversarial Attacks on Combinatorial Multi-Armed Bandits
• ICLR 2024An LLM can Fool Itself: A Prompt-Based Adversarial Attack
• CVPR 2024Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
• NeurIPS 2023A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
• ICML 2023A Law of Robustness beyond Isoperimetry
• ICLR 2023A law of adversarial risk, interpolation, and label noise
• CVPR 2023Adversarial Normalization: I Can Visualize Everything (ICE)
• NeurIPS 2026A Regularization-Based Approach to Public Belief State Search for Adversarial Games
• ICML 2026CaliDist: Calibrating Large Language Models via Behavioral Robustness to Distraction
• ICLR 2026Conformal Robustness Control: A New Strategy for Robust Decision
• CVPR 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large

All Adversarial Robustness papers

331 papers, page 1 of 7

1. ICLR 2026A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
2. ICLR 2026AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization
3. ICLR 2026AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
4. ICLR 2026Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
5. ICLR 2026Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
6. ICLR 2026Adversarially Pretrained Transformers may be Universally Robust In-Context Learners
7. ICLR 2026AEGIS: Adversarial Target–Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models
8. ICLR 2026Are Deep Speech Denoising Models Robust to Adversarial Noise?
9. ICLR 2026Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?
10. ICLR 2026Bandit Learning in Matching Markets Robust to Adversarial Corruptions
11. ICLR 2026Byzantine-Robust Federated Learning with Learnable Aggregation Weights
12. ICLR 2026CERTIFIED VS. EMPIRICAL ADVERSARIAL ROBUSTNESS VIA HYBRID CONVOLUTIONS WITH ATTENTION STOCHASTICITY
13. ICLR 2026Concept-based Adversarial Attack: a Probabilistic Perspective
14. ICLR 2026Conformal Robustness Control: A New Strategy for Robust Decision
15. ICLR 2026Constitutional Classifiers++: Production-Grade Defenses against Universal Jailbreaks
16. ICLR 2026CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering
17. ICLR 2026Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
18. ICLR 2026Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting
19. ICLR 2026Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs
20. ICLR 2026Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
21. ICLR 2026DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
22. ICLR 2026Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
23. ICLR 2026Dual Randomized Smoothing: Beyond Global Noise Variance
24. ICLR 2026Dual-Space Smoothness for Robust and Balanced LLM Unlearning
25. ICLR 2026Efficient Adversarial Attacks on High-dimensional Offline Bandits
26. ICLR 2026Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
27. ICLR 2026EvA: Evolutionary Attacks on Graphs
28. ICLR 2026Exposing and Defending the Achilles' Heel of Video Mixture-of-Experts
29. ICLR 2026f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
30. ICLR 2026FAME: $\underline{F}$ormal $\underline{A}$bstract $\underline{M}$inimal $\underline{E}$xplanation for neural networks
31. ICLR 2026Feature compression is the root cause of adversarial fragility in neural networks
32. ICLR 2026FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation
33. ICLR 2026Fine-Grained Iterative Adversarial Attacks with Limited Computation Budget
34. ICLR 2026GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
35. ICLR 2026Gauge-invariant representation holonomy
36. ICLR 2026Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
37. ICLR 2026Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization
38. ICLR 2026Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models
39. ICLR 2026Jailbreak Transferability Emerges from Shared Representations
40. ICLR 2026Latent Wasserstein Adversarial Imitation Learning
41. ICLR 2026LCA: Local Classifier Alignment for Continual Learning
42. ICLR 2026Learning From Dictionary: Enhancing Robustness of Machine-Generated Text Detection in Zero-Shot Language via Adversarial Training
43. ICLR 2026Learning to Generate Unit Test via Adversarial Reinforcement Learning
44. ICLR 2026LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
45. ICLR 2026Minimax Optimal Adversarial Reinforcement Learning
46. ICLR 2026Model Predictive Adversarial Imitation Learning for Planning from Observation
47. ICLR 2026Nasty Adversarial Training: A Probability Sparsity Perspective for Robustness Enhancement
48. ICLR 2026NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
49. ICLR 2026Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
50. ICLR 2026Nearly Space-Optimal Graph and Hypergraph Sparsification in Insertion-Only Data Streams

FAQ

How many Adversarial Robustness papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,291 in total: 313 in 2023, 334 in 2024, 327 in 2025, 317 in 2026.

How many Adversarial Robustness papers are at NeurIPS 2026?

NeurIPS 2026 has 81 Adversarial Robustness papers, versus 110 the year before.

How many Adversarial Robustness papers are at ICLR 2026?

ICLR 2026 has 94 Adversarial Robustness papers, versus 88 the year before.

How many Adversarial Robustness papers are at ICML 2026?

ICML 2026 has 93 Adversarial Robustness papers, versus 85 the year before.

How many Adversarial Robustness papers are at CVPR 2026?

CVPR 2026 has 49 Adversarial Robustness papers, versus 44 the year before.

Which conference publishes the most Adversarial Robustness papers?

NeurIPS, with 422 papers from 2023 to 2026.