Backdoor Attacks papers, 2023–2026

Key findings

• Backdoor Attacks went from 73 papers in 2023 to 111 in 2026, roughly 1.5x in three years.
• NeurIPS publishes the most Backdoor Attacks work: 124 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 0 in 2023 to 16 in 2026.
• Among the 5 topics under Security and Trust, it ranks #2 by 2026 paper count; the fastest grower in the group, Watermarking, is up 9.3x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Theoretical Analysis of Backdoor Learning as Simplicity-Biased Optimization Dynamics
• ICML 2026Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning
• ICLR 2026Defending against Backdoor Attacks via Module Switching
• CVPR 2026Eliminate Distance Differences Induced by Backdoor Attacks Layer-Selective Training and
• NeurIPS 2025A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
• ICML 2025A Closer Look at Backdoor Attacks on CLIP
• ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
• CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
• NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
• ICML 2024Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
• ICLR 2024Adversarial Feature Map Pruning for Backdoor
• CVPR 2024Data Poisoning based Backdoor Attacks to Contrastive Learning
• NeurIPS 2023A Unified Detection Framework for Inference-Stage Backdoor Defenses
• ICML 2023Data Poisoning Attacks Against Multimodal Encoders
• ICLR 2023Adversarial Attacks on Adversarial Bandits
• CVPR 2023Architectural Backdoors in Neural Networks
• NeurIPS 2026AI Models Can Provably Hide Arbitrary Capabilities
• ICML 2026DF-LoGiT: Data-Free Logic-Gated Backdoor Attacks in Vision Transformers
• ICLR 2026Don't Shift the Trigger: Robust Gradient Ascent for Backdoor Unlearning
• CVPR 2026Logit-Margin Repulsion for Backdoor Defense

All Backdoor Attacks papers

380 papers, page 7 of 8

301. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
302. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
303. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
304. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits
305. NeurIPS 2024Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
306. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
307. NeurIPS 2024WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
308. CVPR 2023Architectural Backdoors in Neural Networks
309. CVPR 2023Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger
310. CVPR 2023Backdoor Cleansing With Unlabeled Data
311. CVPR 2023Backdoor Defense via Adaptively Splitting Poisoned Dataset
312. CVPR 2023Backdoor Defense via Deconfounded Representation Learning
313. CVPR 2023Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
314. CVPR 2023Color Backdoor: A Robust Poisoning Attack in Color Space
315. CVPR 2023Defending Against Patch-Based Backdoor Attacks on Self-Supervised Learning
316. CVPR 2023Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
317. CVPR 2023Detecting Backdoors in Pre-Trained Encoders
318. CVPR 2023Dynamic Generative Targeted Attacks With Pattern Injection
319. CVPR 2023Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-Based Attacks
320. CVPR 2023Enhancing the Self-Universality for Transferable Targeted Attacks
321. CVPR 2023Ensemble-Based Blackbox Attacks on Dense Prediction
322. CVPR 2023How to Backdoor Diffusion Models?
323. CVPR 2023MEDIC: Remove Model Backdoors via Importance Driven Cloning
324. CVPR 2023Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks
325. CVPR 2023Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks
326. CVPR 2023Re-Thinking Model Inversion Attacks Against Deep Neural Networks
327. CVPR 2023Reinforcement Learning-Based Black-Box Model Inversion Attacks
328. CVPR 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition
329. CVPR 2023Single Image Backdoor Inversion via Robust Smoothed Classifiers
330. CVPR 2023The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks
331. CVPR 2023The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection
332. CVPR 2023TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets
333. CVPR 2023You Are Catching My Attention: Are Vision Transformers Bad Learners Under Backdoor Attacks?
334. ICLR 2023Adversarial Attacks on Adversarial Bandits
335. ICLR 2023Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
336. ICLR 2023Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
337. ICLR 2023Distilling Cognitive Backdoor Patterns within an Image
338. ICLR 2023Effective passive membership inference attacks in federated learning against overparameterized models
339. ICLR 2023Few-shot Backdoor Attacks via Neural Tangent Kernels
340. ICLR 2023FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
341. ICLR 2023Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
342. ICLR 2023Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
343. ICLR 2023Revisiting the Assumption of Latent Separability for Backdoor Defenses
344. ICLR 2023SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
345. ICLR 2023The Dark Side of AutoML: Towards Architectural Backdoor Search
346. ICLR 2023Towards Robustness Certification Against Universal Perturbations
347. ICLR 2023TrojText: Test-time Invisible Textual Trojan Insertion
348. ICLR 2023UNICORN: A Unified Backdoor Trigger Inversion Framework
349. ICML 2023Are Diffusion Models Vulnerable to Membership Inference Attacks?
350. ICML 2023Data Poisoning Attacks Against Multimodal Encoders

FAQ

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

381 in total: 73 in 2023, 105 in 2024, 92 in 2025, 111 in 2026.

How many Backdoor Attacks papers are at NeurIPS 2026?

NeurIPS 2026 has 36 Backdoor Attacks papers, versus 31 the year before.

How many Backdoor Attacks papers are at ICLR 2026?

ICLR 2026 has 20 Backdoor Attacks papers, versus 25 the year before.

How many Backdoor Attacks papers are at ICML 2026?

ICML 2026 has 36 Backdoor Attacks papers, versus 17 the year before.

How many Backdoor Attacks papers are at CVPR 2026?

CVPR 2026 has 19 Backdoor Attacks papers, versus 19 the year before.

Which conference publishes the most Backdoor Attacks papers?

NeurIPS, with 124 papers from 2023 to 2026.