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 3 of 8

101. NeurIPS 2026ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers
102. NeurIPS 2026Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
103. NeurIPS 2026The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training
104. NeurIPS 2026Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
105. NeurIPS 2026Towards Universal Black-box Attacks on Graph Neural Networks
106. NeurIPS 2026TraceGuard: Defending Multi-Turn Jailbreak Attacks via Prompt-Response Risk Signal Tracking
107. NeurIPS 2026Training-Based Backdoors Are Not Cryptographic
108. NeurIPS 2026VOID: Backdoor Injection through Knowledge Vacuity in Federated Unlearning
109. NeurIPS 2026When Sanitization Becomes the Trigger: Defense-Triggered Backdoor Attacks
110. NeurIPS 2026Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning
111. CVPR 2025BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
112. CVPR 2025Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
113. CVPR 2025Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices
114. CVPR 2025DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders
115. CVPR 2025Detecting Backdoor Attacks in Federated Learning via Direction Alignment Inspection
116. CVPR 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations
117. CVPR 2025EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection
118. CVPR 2025Improving Transferable Targeted Attacks with Feature Tuning Mixup
119. CVPR 2025Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning
120. CVPR 2025Invisible Backdoor Attack against Self-supervised Learning
121. CVPR 2025Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis
122. CVPR 2025Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
123. CVPR 2025PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection
124. CVPR 2025Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
125. CVPR 2025Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
126. CVPR 2025Test-Time Backdoor Detection for Object Detection Models
127. CVPR 2025UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
128. CVPR 2025Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models
129. CVPR 2025Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation
130. ICLR 2025Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
131. ICLR 2025Adversarial Training for Defense Against Label Poisoning Attacks
132. ICLR 2025Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
133. ICLR 2025AI2TALE: An Innovative Information Theory-based Approach for Learning to Localize Phishing Attacks
134. ICLR 2025Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning
135. ICLR 2025Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
136. ICLR 2025Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
137. ICLR 2025Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
138. ICLR 2025Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
139. ICLR 2025Detecting Backdoor Samples in Contrastive Language Image Pretraining
140. ICLR 2025DocMIA: Document-Level Membership Inference Attacks against DocVQA Models
141. ICLR 2025Energy-based Backdoor Defense Against Federated Graph Learning
142. ICLR 2025GPromptShield: Elevating Resilience in Graph Prompt Tuning Against Adversarial Attacks
143. ICLR 2025Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
144. ICLR 2025Injecting Universal Jailbreak Backdoors into LLMs in Minutes
145. ICLR 2025Machine Unlearning Fails to Remove Data Poisoning Attacks
146. ICLR 2025Mind Control through Causal Inference: Predicting Clean Images from Poisoned Data
147. ICLR 2025Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
148. ICLR 2025Protecting against simultaneous data poisoning attacks
149. ICLR 2025Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
150. ICLR 2025REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

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.