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

124 papers, page 2 of 3

51. NeurIPS 2025Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?
52. NeurIPS 2025Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
53. NeurIPS 2025LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks
54. NeurIPS 2025MARS: A Malignity-Aware Backdoor Defense in Federated Learning
55. NeurIPS 2025Provable Watermarking for Data Poisoning Attacks
56. NeurIPS 2025RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models
57. NeurIPS 2025SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
58. NeurIPS 2025SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
59. NeurIPS 2025Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
60. NeurIPS 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
61. NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
62. NeurIPS 2025The Good, the Bad and the Ugly: Meta-Analysis of Watermarks, Transferable Attacks and Adversarial Defenses
63. NeurIPS 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
64. NeurIPS 2025Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning
65. NeurIPS 2025TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks
66. NeurIPS 2025Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
67. NeurIPS 2025Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers
68. NeurIPS 20242D-OOB: Attributing Data Contribution Through Joint Valuation Framework
69. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
70. NeurIPS 2024BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
71. NeurIPS 2024BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
72. NeurIPS 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
73. NeurIPS 2024BAN: Detecting Backdoors Activated by Adversarial Neuron Noise
74. NeurIPS 2024Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
75. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
76. NeurIPS 2024Data Free Backdoor Attacks
77. NeurIPS 2024Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
78. NeurIPS 2024Faster Repeated Evasion Attacks in Tree Ensembles
79. NeurIPS 2024Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
80. NeurIPS 2024Full-Distance Evasion of Pedestrian Detectors in the Physical World
81. NeurIPS 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
82. NeurIPS 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
83. NeurIPS 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
84. NeurIPS 2024LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect
85. NeurIPS 2024Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
86. NeurIPS 2024Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
87. NeurIPS 2024OSLO: One-Shot Label-Only Membership Inference Attacks
88. NeurIPS 2024Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
89. NeurIPS 2024Pseudo-Private Data Guided Model Inversion Attacks
90. NeurIPS 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
91. NeurIPS 2024Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
92. NeurIPS 2024Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
93. NeurIPS 2024SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
94. NeurIPS 2024Scanning Trojaned Models Using Out-of-Distribution Samples
95. NeurIPS 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
96. NeurIPS 2024Stealth edits to large language models
97. NeurIPS 2024Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
98. NeurIPS 2024Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
99. NeurIPS 2024Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
100. NeurIPS 2024Unelicitable Backdoors via Cryptographic Transformer Circuits

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.