Overview

Software security examines how flaws arise in programs and systems, how attackers can exploit them, and how developers can prevent or fix them. Common approaches include static analysis and taint tracking, dynamic testing and fuzzing, dependency and vulnerability analysis, threat modeling, and formal verification. Large language models and coding agents are increasingly applied to vulnerability detection, exploit reproduction, and patch generation, with evaluation using CWE- and CVE-based tasks, fuzzing targets, and smart-contract tests. A central challenge is that functional tests and static checks do not establish security: tools must balance missed flaws against false alarms, and generated fixes need realistic validation before deployment.

Latest papers

CardsList

99 papers4 papers in the last four weeks, down 69% on the four weeks before. 0.0% of all new papers.

  1. Does Frontier AI Strengthen Cyber Defense? Evidence from Project Glasswing

    Nov 4, 2026Thomas MoskCybersecuritySoftware Security

  2. A Hybrid Approach for Automated Security Pattern Recovery

    Nov 4, 2026Anh Minh Nguyen, Tuan Dat Tran, Alzubair Hassan +1Software Security

  3. Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation

    Oct 23, 2026Zifan Peng, Peng Huang, Jingyi Zheng +5Software SecuritySynthetic Benchmark Generation

  4. WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications

    Oct 22, 2026Ilaria Campestrini, Stefano Zanero, Engin KirdaSoftware SecurityAnomaly Detection

  5. Many Repairs, One Direction: Steering Code Models Toward Safer Cryptographic API Use

    Oct 18, 2026Tianhe Lu, Sakuna Harinda Jayasundara, Eric Spero +3Secure Code GenerationLLM Code Generation

  6. P2Patch: Exploit-Guided Vulnerability Repair

    Oct 14, 2026Mohsen Iranmanesh, Sina Moradi Sabet, Sina Marefat +7Automated Exploit GenerationAutomated Program Repair

  7. Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications

    Oct 13, 2026Yang Luo, Tiantian Ji, Zifeng Kang +4Software SecurityPrompt Injection Attacks

  8. Security in LLM-Assisted Coding: A Systematic Literature Review

    Oct 11, 2026Liang Yuan, Maryam Khanian Najafabadi, Mashud Rana +1LLM SecuritySoftware Security

  9. Last Secure Code Benchmark: Is the Code You Vibe Secure?

    Oct 10, 2026Tianyi Wu, Chao Ge, Peng Chen +12Secure Code GenerationAI Agent Security Benchmarks

  10. Polar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization and Mitigation

    Oct 5, 2026Luoxi Tang, Yuqiao Meng, Ankita Patra +3CybersecurityCyber Threat Intelligence

  11. From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review

    Oct 2, 2026Akash Iyer, Taha Demirkan, Keerthi Koneru +3CybersecuritySoftware Security

  12. AuraForge: Scaling Security Supervision for Training Coding Agents

    Oct 1, 2026Danqing Wang, Songwen Zhao, Harsh Sharma +4AI Coding AgentsSoftware Security

  13. SecureVibe: Making Vibe Coding More Secure

    Sep 29, 2026Danqing Wang, Baolin Peng, Zhepei Wei +8Secure Code GenerationSoftware Security

  14. Evaluating Coding Agents on Kernel Exploit Generation

    Sep 22, 2026Junyoung Jang, Gwanhyun Lee, Hwiwon Lee +4AI Coding AgentsSoftware Security

  15. Identifying Security Platform Product Abuse with Machine Learning

    Sep 18, 2026Shaefer Drew, Michael Brautbar, Paul Knight +6Software SecurityAnomaly Detection

  16. Seeing is Not Believing: Breaking the Physical-to-Digital Trust Boundary in Robotics

    Sep 8, 2026Leming Shen, Shikai Geng, Yuanqing Zheng +1CybersecuritySoftware Security

  17. VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

    Sep 7, 2026Jiahao Shi, Edward Tsien, Yifeng Di +10LLM Agent EvaluationSoftware Security

  18. CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

    Sep 2, 2026Varun Gadey, Ziad Marey, Alexandra DmitrienkoRetrieval-Augmented Code GenerationData Poisoning Attacks

  19. Automated Vulnerability Injection in Smart Contracts Using Large Language Models

    Sep 2, 2026Luca Migliaccio, Roberto Natella, Naghmeh Ivaki +2Software SecuritySoftware Vulnerability Detection

  20. Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion

    Sep 1, 2026Phong Trinh Duy, Trang Dang Yen, Hung Nguyen-Huu +5Software SecurityKG Completion

  21. Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems

    Aug 26, 2026Ilai Shraga, Roei Eshel, Lior GorelikLLM GuardrailsSoftware Security

  22. MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration

    Aug 26, 2026Miseon Yu, Jaehoon Choi, Younghan Lee +1Code GenerationSecure Code Generation

  23. Evaluating and Preventing Security Smells in AI-Generated Ansible Code

    Aug 25, 2026Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge +1Secure Code GenerationSoftware Security

  24. Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races

    Aug 25, 2026Zihao Zheng, Jiayu Long, Baichuan Li +1Runtime Enforcement for AI AgentsLLM Agent Safety