Latest Research in Cryptography and Security

Top Research Topics in Cryptography and Security

• Cryptography and Security — 45 papers
• Software Engineering — 32 papers
• Software Engineering Research — 15 papers
• Machine Learning — 9 papers
• Artificial Intelligence — 8 papers
• Computation and Language — 6 papers
• Machine Learning — 3 papers
• Information and Cyber Security — 3 papers
• Adversarial Robustness in Machine Learning — 3 papers
• Scientific Computing and Data Management — 3 papers

Highest-Cited Papers

1. Size Classification for Software Maintenance Projects Through a Simplified Minimalist Machine Learning Algorithm
2. Stress-Testing Byzantine Robustness in Multi-Agent LLM Systems: Adaptive Adversaries and an Alternative Filtering Anchor
3. Bug Whisperer: Unleashing LLMs to Craft Context-Aware Tests Guided by Path Constraints and Bug Clues
4. Multi-modal artificial intelligence-driven code quality prediction and self-healing automation using self-modulating convolutional neural networks
5. Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models
6. MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS
7. Watermarking Diffusion Language Models
8. FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement
9. Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
10. Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
11. CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
12. Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks
13. Detecting Argument-Swap Bugs Using Context-Enhanced Code Representations
14. Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks
15. Predictive Likelihood Ratios for Language Model Watermark Detection
16. ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
17. Misleading the Planner through Deceptive Resumes: Registration-Time Injection in Centralized Multi-Agent Systems
18. BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
19. Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
20. Quiet or Blind? Measuring the Cost of Exclusions in LLM-Generated Detection Rules