Latest Research in Artificial Intelligence

Top Research Topics in Artificial Intelligence

• Cryptography and Security — 37 papers
• Software Engineering — 8 papers
• Artificial Intelligence — 4 papers
• Software Engineering Research — 3 papers
• Security and Verification in Computing — 3 papers
• Adversarial Robustness in Machine Learning — 3 papers
• Scientific Computing and Data Management — 2 papers
• Software Testing and Debugging Techniques — 2 papers
• Topic Modeling — 2 papers
• Human-Computer Interaction — 1 papers

Highest-Cited Papers

1. Character-level Perturbations in Software Requirements : Evaluating Transformer Models Robustness Across Learning Paradigms and Classification Tasks
2. Toward Reproducible Local Evaluation of Prompt Injection in Open-Weight LLMs: Design and Threat Model
3. Toward Reproducible Local Evaluation of Prompt Injection in Open-Weight LLMs: Design and Threat Model
4. EviRCA: Decoupling Evidence Extraction from Reasoning for Microservice Root-Cause Analysis
5. Effective and Efficient Threat Hunting with Small Language Models
6. AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
7. The Illusion of Local Privacy: Confidentiality Boundary Failures in Consumer LLM Serving Systems
8. Experimental Settings in LLM-Based Program Repair: A Study of Inputs, Tool Access, Feedback, and Validation
9. A11yLTLNav: Automatic Detection of Accessibility Navigation Failures
10. When Agents See Differently: Exposing UI Desynchronization Threats in Mobile Agents
11. CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement
12. Trust propagation and structural containment in Multi-agent LLM pipelines
13. Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair
14. When is LLM-Based Program Reasoning Correct? A Completion Semantics for LLM-Based Code Inference
15. Can We Stop Malicious AI? KILLBENCH: A Benchmark for External AI Kill Switch Feasibility
16. AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
17. What Does a Repair Statistic Measure? A Claim-Indexed Audit of Repository-Level LLM Repair
18. What Does a Repair Statistic Measure? A Claim-Indexed Audit of Repository-Level LLM Repair
19. A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility
20. SkillAtlas: An Attack Trace Library for Agent Skills