Applications · security papers, 2023–2026

Key findings

• Applications · security went from 3 papers in 2023 to 10 in 2026, roughly 3.3x in three years.
• NeurIPS publishes the most Applications · security work: 11 papers from 2023 to 2026, 39% of the four-venue total.
• Among the 10 topics under Application Domains, it ranks #8 by 2026 paper count; the fastest grower in the group, Applications · health medicine, is up 61x versus 3.3x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Embedding Security Properties into AI-Enabled Cyber-Physical Systems
• ICML 2026Exploring Motif-based Heterogeneous Graph Learning for ReDoS Detection
• ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
• CVPR 2026Enhancing the Security of Visual Speaker Authentication Based on Dynamic
• NeurIPS 2025Antidistillation Sampling
• ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
• ICLR 2025Safety Layers in Aligned Large Language Models: The Key to LLM Security
• CVPR 2025Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning
• NeurIPS 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
• ICLR 2024Language Model Inversion
• CVPR 2024Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space
• NeurIPS 2023Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction
• CVPR 2023RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis
• NeurIPS 2026Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid Security
• ICML 2026One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
• ICLR 2026Every Language Model Has a Forgery-Resistant Signature
• NeurIPS 2025SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
• ICML 2025Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
• NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
• NeurIPS 2023Label Poisoning is All You Need

All Applications · security papers

28 papers, page 1 of 1

1. CVPR 2026Enhancing the Security of Visual Speaker Authentication Based on Dynamic
2. ICLR 2026Every Language Model Has a Forgery-Resistant Signature
3. ICLR 2026Intrinsic Explanation of Random Subspace Method for Enhanced Security Applications
4. ICML 2026Beyond Rewards in RL for Cyber Defence
5. ICML 2026CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability
6. ICML 2026Exploring Motif-based Heterogeneous Graph Learning for ReDoS Detection
7. ICML 2026One Bug, Hundreds Behind: LLMs for Large-Scale Bug Discovery
8. ICML 2026OpenSage: Self-programming Agent Generation Engine
9. NeurIPS 2026Certified Single-Level Reformulation for Tri-Level Cyber-Physical Grid Security
10. NeurIPS 2026Embedding Security Properties into AI-Enabled Cyber-Physical Systems
11. CVPR 2025Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning
12. ICLR 2025Safety Layers in Aligned Large Language Models: The Key to LLM Security
13. ICML 2025Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security
14. ICML 2025EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
15. ICML 2025Pixel2Feature Attack (P2FA): Rethinking the Perturbed Space to Enhance Adversarial Transferability
16. ICML 2025Position: Certified Robustness Does Not (Yet) Imply Model Security
17. NeurIPS 2025Antidistillation Sampling
18. NeurIPS 2025Self-Supervised Learning of Graph Representations for Network Intrusion Detection
19. NeurIPS 2025SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
20. CVPR 2024Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space
21. ICLR 2024Language Model Inversion
22. NeurIPS 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
23. NeurIPS 2024Can Simple Averaging Defeat Modern Watermarks?
24. NeurIPS 2024Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
25. NeurIPS 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
26. CVPR 2023RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis
27. NeurIPS 2023Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction
28. NeurIPS 2023Label Poisoning is All You Need

FAQ

How many Applications · security papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

28 in total: 3 in 2023, 6 in 2024, 9 in 2025, 10 in 2026.

How many Applications · security papers are at NeurIPS 2026?

NeurIPS 2026 has 2 Applications · security papers, versus 3 the year before.

How many Applications · security papers are at ICLR 2026?

ICLR 2026 has 2 Applications · security papers, versus 1 the year before.

How many Applications · security papers are at ICML 2026?

ICML 2026 has 5 Applications · security papers, versus 4 the year before.

How many Applications · security papers are at CVPR 2026?

CVPR 2026 has 1 Applications · security papers, versus 1 the year before.

Which conference publishes the most Applications · security papers?

NeurIPS, with 11 papers from 2023 to 2026.