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 6 of 8

251. ICML 2024Causality Based Front-door Defense Against Backdoor Attack on Language Models
252. ICML 2024Data Poisoning Attacks against Conformal Prediction
253. ICML 2024DataFreeShield: Defending Adversarial Attacks without Training Data
254. ICML 2024Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normalization
255. ICML 2024Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
256. ICML 2024Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
257. ICML 2024Fast Adversarial Attacks on Language Models In One GPU Minute
258. ICML 2024FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
259. ICML 2024Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
260. ICML 2024IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
261. ICML 2024Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
262. ICML 2024Low-Cost High-Power Membership Inference Attacks
263. ICML 2024Membership Inference Attacks on Diffusion Models via Quantile Regression
264. ICML 2024Privacy Attacks in Decentralized Learning
265. ICML 2024Revisiting Character-level Adversarial Attacks for Language Models
266. ICML 2024SHINE: Shielding Backdoors in Deep Reinforcement Learning
267. ICML 2024SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign Decoding
268. ICML 2024TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
269. ICML 2024The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
270. ICML 2024The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline
271. ICML 2024Toward Availability Attacks in 3D Point Clouds
272. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
273. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
274. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
275. NeurIPS 2024BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
276. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
277. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
278. NeurIPS 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
279. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
280. NeurIPS 2024Data Free Backdoor Attacks
281. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
282. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
283. NeurIPS 2024Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
284. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
285. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
286. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
287. NeurIPS 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
288. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
289. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
290. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
291. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
292. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
293. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
294. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
295. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
296. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
297. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
298. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
299. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
300. NeurIPS 2024Stealth edits to large language models

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.