对抗鲁棒论文趋势 2023–2026

主要结论

• 对抗鲁棒论文从 2023 年的 313 篇增长到 2026 年的 317 篇，三年间扩大到约 1.0 倍。
• NeurIPS 是发对抗鲁棒论文最多的会议，2023–2026 年共 422 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是对齐与安全：同时属于两个主题的论文从 2023 年的 13 篇增至 2026 年的 56 篇。
• 在「安全与可信」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的水印是 9.3 倍，对抗鲁棒是 1.0 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部对抗鲁棒论文

共 1,290 篇，第 7 / 26 页

301. NeurIPS 2026Stable Alpha: Adversarial Invariant Representation Learning for Nonlinear Asset Pricing under Temporal Distribution Shifts
302. NeurIPS 2026Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
303. NeurIPS 2026Surrogate Calibration for Transferable Adversarial Attacks against Black-Box MLLMs
304. NeurIPS 2026SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
305. NeurIPS 2026Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data
306. NeurIPS 2026Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
307. NeurIPS 2026The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
308. NeurIPS 2026The Web Doesn't Sit Still: Adversarial Self-Evolving Attacks on Search Agents
309. NeurIPS 2026Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
310. NeurIPS 2026Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation
311. NeurIPS 2026Variational Cover Modification Steganography
312. NeurIPS 2026When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective
313. NeurIPS 2026When Are Semivalue-Based Decisions Identifiable? Robust Data Selection under Utility Ambiguity
314. NeurIPS 2026When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
315. NeurIPS 2026When to Inject the Target: Stage-Decoupled Guidance for Diffusion-Based Targeted Adversarial Attacks
316. NeurIPS 2026When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors
317. CVPR 2025A Unified, Resilient, and Explainable Adversarial Patch Detector
318. CVPR 2025A3: Few-shot Prompt Learning of Unlearnable Examples with Cross-Modal Adversarial Feature Alignment
319. CVPR 2025Advancing Adversarial Robustness in GNeRFs: The IL2-NeRF Attack
320. CVPR 2025Boosting Adversarial Transferability through Augmentation in Hypothesis Space
321. CVPR 2025Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks
322. CVPR 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
323. CVPR 2025Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
324. CVPR 2025Detecting Adversarial Data Using Perturbation Forgery
325. CVPR 2025Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification
326. CVPR 2025Doppelgangers and Adversarial Vulnerability
327. CVPR 2025Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training
328. CVPR 2025Enhancing Testing-Time Robustness for Trusted Multi-View Classification in the Wild
329. CVPR 2025Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
330. CVPR 2025FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering
331. CVPR 2025Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes
332. CVPR 2025Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization
333. CVPR 2025IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
334. CVPR 2025Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
335. CVPR 2025Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation
336. CVPR 2025Instant Adversarial Purification with Adversarial Consistency Distillation
337. CVPR 2025Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection
338. CVPR 2025MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation
339. CVPR 2025Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
340. CVPR 2025MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework
341. CVPR 2025NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
342. CVPR 2025On the Zero-shot Adversarial Robustness of Vision-Language Models: A Truly Zero-shot and Training-free Approach
343. CVPR 2025PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
344. CVPR 2025ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector
345. CVPR 2025Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound Images
346. CVPR 2025R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
347. CVPR 2025RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection
348. CVPR 2025RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions
349. CVPR 2025Rethinking the Adversarial Robustness of Multi-Exit Neural Networks in an Attack-Defense Game
350. CVPR 2025Saliuitl: Ensemble Salience Guided Recovery of Adversarial Patches against CNNs

常见问题

2023–2026 年四大会议一共有多少篇对抗鲁棒论文？

共 1,291 篇，按年份分别是 2023 年 313 篇、2024 年 334 篇、2025 年 327 篇、2026 年 317 篇。

NeurIPS 2026 有多少篇对抗鲁棒论文？

NeurIPS 2026 有 81 篇对抗鲁棒论文，上一届是 110 篇。

ICLR 2026 有多少篇对抗鲁棒论文？

ICLR 2026 有 94 篇对抗鲁棒论文，上一届是 88 篇。

ICML 2026 有多少篇对抗鲁棒论文？

ICML 2026 有 93 篇对抗鲁棒论文，上一届是 85 篇。

CVPR 2026 有多少篇对抗鲁棒论文？

CVPR 2026 有 49 篇对抗鲁棒论文，上一届是 44 篇。

哪个会议的对抗鲁棒论文最多？

NeurIPS，2023–2026 年共 422 篇。